Artificial Intelligence Nanodegree

Computer Vision Capstone

Project: Facial Keypoint Detection

---

Welcome to the final Computer Vision project in the Artificial Intelligence Nanodegree program!

In this project, you’ll combine your knowledge of computer vision techniques and deep learning to build and end-to-end facial keypoint recognition system! Facial keypoints include points around the eyes, nose, and mouth on any face and are used in many applications, from facial tracking to emotion recognition.

There are three main parts to this project:

Part 1 : Investigating OpenCV, pre-processing, and face detection

Part 2 : Training a Convolutional Neural Network (CNN) to detect facial keypoints

Part 3 : Putting parts 1 and 2 together to identify facial keypoints on any image!

---

*Here's what you need to know to complete the project:

1. In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested.

   a. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!

1. In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation.

   a. Each section where you will answer a question is preceded by a 'Question X' header.

   b. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'.

Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.

The rubric contains optional suggestions for enhancing the project beyond the minimum requirements. If you decide to pursue the "(Optional)" sections, you should include the code in this IPython notebook.

Your project submission will be evaluated based on your answers to each of the questions and the code implementations you provide.

Steps to Complete the Project

Each part of the notebook is further broken down into separate steps. Feel free to use the links below to navigate the notebook.

In this project you will get to explore a few of the many computer vision algorithms built into the OpenCV library. This expansive computer vision library is now almost 20 years old and still growing!

The project itself is broken down into three large parts, then even further into separate steps. Make sure to read through each step, and complete any sections that begin with '(IMPLEMENTATION)' in the header; these implementation sections may contain multiple TODOs that will be marked in code. For convenience, we provide links to each of these steps below.

Part 1 : Investigating OpenCV, pre-processing, and face detection

• Step 0: Detect Faces Using a Haar Cascade Classifier
• Step 1: Add Eye Detection
• Step 2: De-noise an Image for Better Face Detection
• Step 3: Blur an Image and Perform Edge Detection
• Step 4: Automatically Hide the Identity of an Individual

Part 2 : Training a Convolutional Neural Network (CNN) to detect facial keypoints

• Step 5: Create a CNN to Recognize Facial Keypoints
• Step 6: Compile and Train the Model
• Step 7: Visualize the Loss and Answer Questions

Part 3 : Putting parts 1 and 2 together to identify facial keypoints on any image!

• Step 8: Build a Robust Facial Keypoints Detector (Complete the CV Pipeline)

---

Step 0: Detect Faces Using a Haar Cascade Classifier

Have you ever wondered how Facebook automatically tags images with your friends' faces? Or how high-end cameras automatically find and focus on a certain person's face? Applications like these depend heavily on the machine learning task known as face detection - which is the task of automatically finding faces in images containing people.

At its root face detection is a classification problem - that is a problem of distinguishing between distinct classes of things. With face detection these distinct classes are 1) images of human faces and 2) everything else.

We use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images. OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the detector_architectures directory.

Import Resources

In the next python cell, we load in the required libraries for this section of the project.

# Import required libraries for this section

%matplotlib inline

import numpy as np
import matplotlib.pyplot as plt
import math
import cv2                     # OpenCV library for computer vision
from PIL import Image
import time 

Next, we load in and display a test image for performing face detection.

Note: by default OpenCV assumes the ordering of our image's color channels are Blue, then Green, then Red. This is slightly out of order with most image types we'll use in these experiments, whose color channels are ordered Red, then Green, then Blue. In order to switch the Blue and Red channels of our test image around we will use OpenCV's cvtColor function, which you can read more about by checking out some of its documentation located here. This is a general utility function that can do other transformations too like converting a color image to grayscale, and transforming a standard color image to HSV color space.

# Load in color image for face detection
image = cv2.imread('images/test_image_1.jpg')

# Convert the image to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Plot our image using subplots to specify a size and title
fig = plt.figure(figsize = (8, 8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Original Image')
ax1.imshow(image)

<matplotlib.image.AxesImage at 0x7fd9655df470>

There are a lot of people - and faces - in this picture. 13 faces to be exact! In the next code cell, we demonstrate how to use a Haar Cascade classifier to detect all the faces in this test image.

This face detector uses information about patterns of intensity in an image to reliably detect faces under varying light conditions. So, to use this face detector, we'll first convert the image from color to grayscale.

Then, we load in the fully trained architecture of the face detector -- found in the file haarcascade_frontalface_default.xml - and use it on our image to find faces!

To learn more about the parameters of the detector see this post.

# Convert the RGB  image to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)

# Extract the pre-trained face detector from an xml file
face_cascade = cv2.CascadeClassifier('detector_architectures/haarcascade_frontalface_default.xml')

# Detect the faces in image
faces = face_cascade.detectMultiScale(gray, 4, 6)

# Print the number of faces detected in the image
print('Number of faces detected:', len(faces))

# print(faces) --> [1295   94   96   96] --> (x,y,w,h) --> position and dimension of the feature

# Make a copy of the orginal image to draw face detections on
image_with_detections = np.copy(image)

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 3)
    

# Display the image with the detections
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with Face Detections')
ax1.imshow(image_with_detections)

Number of faces detected: 13

<matplotlib.image.AxesImage at 0x7fd964d1eb00>

In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.

---

Step 1: Add Eye Detections

There are other pre-trained detectors available that use a Haar Cascade Classifier - including full human body detectors, license plate detectors, and more. A full list of the pre-trained architectures can be found here.

To test your eye detector, we'll first read in a new test image with just a single face.

# Load in color image for face detection
image = cv2.imread('images/james.jpg')

# image = cv2.imread('images/gus.jpg') --> faces = face_cascade.detectMultiScale(gray, 1.29, 6) 

# Convert the image to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Plot the RGB image
fig = plt.figure(figsize = (6,6))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Original Image')
ax1.imshow(image)

<matplotlib.image.AxesImage at 0x7fd964044898>

Notice that even though the image is a black and white image, we have read it in as a color image and so it will still need to be converted to grayscale in order to perform the most accurate face detection.

So, the next steps will be to convert this image to grayscale, then load OpenCV's face detector and run it with parameters that detect this face accurately.

# Convert the RGB  image to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)

# Extract the pre-trained face detector from an xml file
face_cascade = cv2.CascadeClassifier('detector_architectures/haarcascade_frontalface_default.xml')

# Detect the faces in image
faces = face_cascade.detectMultiScale(gray, 1.25, 6) 

# Print the number of faces detected in the image
print('Number of faces detected:', len(faces))

# Make a copy of the orginal image to draw face detections on
image_with_detections = np.copy(image)

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 2)
    
# Display the image with the detections
fig = plt.figure(figsize = (6,6))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with Face Detection')
ax1.imshow(image_with_detections)

Number of faces detected: 1

<matplotlib.image.AxesImage at 0x7fd96401ee80>

(IMPLEMENTATION) Add an eye detector to the current face detection setup.

A Haar-cascade eye detector can be included in the same way that the face detector was and, in this first task, it will be your job to do just this.

To set up an eye detector, use the stored parameters of the eye cascade detector, called haarcascade_eye.xml, located in the detector_architectures subdirectory. In the next code cell, create your eye detector and store its detections.

A few notes before you get started:

First, make sure to give your loaded eye detector the variable name

eye_cascade

and give the list of eye regions you detect the variable name

eyes

Second, since we've already run the face detector over this image, you should only search for eyes within the rectangular face regions detected in faces. This will minimize false detections.

Lastly, once you've run your eye detector over the facial detection region, you should display the RGB image with both the face detection boxes (in red) and your eye detections (in green) to verify that everything works as expected.

# Extract the pre-trained eyes detector from an xml file
eye_cascade = cv2.CascadeClassifier('detector_architectures/haarcascade_eye.xml')

# Make a copy of the original image to plot rectangle detections
image_with_detections = np.copy(image)   

# Loop over the detections and draw their corresponding face detection boxes
for (x,y,w,h) in faces:
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h),(255,0,0), 3)  # detect faces
    
    roi_gray = gray[y:y+h, x:x+w]
    roi_color = image_with_detections[y:y+h, x:x+w]    
    eyes = eye_cascade.detectMultiScale(roi_gray)
    
    for (ex,ey,ew,eh) in eyes: # for each detected face, eyes will be detected as well
        cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),2)

# Plot the image with both faces and eyes detected
fig = plt.figure(figsize = (6,6))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with Face and Eye Detection')
ax1.imshow(image_with_detections)

<matplotlib.image.AxesImage at 0x7fd95c7f8358>

(Optional) Add face and eye detection to your laptop camera

It's time to kick it up a notch, and add face and eye detection to your laptop's camera! Afterwards, you'll be able to show off your creation like in the gif shown below - made with a completed version of the code!

Notice that not all of the detections here are perfect - and your result need not be perfect either. You should spend a small amount of time tuning the parameters of your detectors to get reasonable results, but don't hold out for perfection. If we wanted perfection we'd need to spend a ton of time tuning the parameters of each detector, cleaning up the input image frames, etc. You can think of this as more of a rapid prototype.

The next cell contains code for a wrapper function called laptop_camera_face_eye_detector that, when called, will activate your laptop's camera. You will place the relevant face and eye detection code in this wrapper function to implement face/eye detection and mark those detections on each image frame that your camera captures.

Before adding anything to the function, you can run it to get an idea of how it works - a small window should pop up showing you the live feed from your camera; you can press any key to close this window.

Note: Mac users may find that activating this function kills the kernel of their notebook every once in a while. If this happens to you, just restart your notebook's kernel, activate cell(s) containing any crucial import statements, and you'll be good to go!

### Add face and eye detection to this laptop camera function 
# Make sure to draw out all faces/eyes found in each frame on the shown video feed

import cv2
import time 

# wrapper function for face/eye detection with your laptop camera
def laptop_camera_go():
    # Create instance of video capturer
    cv2.namedWindow("face detection activated")
    vc = cv2.VideoCapture(0)

    # Try to get the first frame
    if vc.isOpened(): 
        rval, frame = vc.read()
    else:
        rval = False
    
    # Keep the video stream open
    while rval:
        # Plot the image from camera with all the face and eye detections marked
        cv2.imshow("face detection activated", frame)
        
        # Exit functionality - press any key to exit laptop video
        key = cv2.waitKey(20)
        if key > 0: # Exit by pressing any key
            # Destroy windows 
            cv2.destroyAllWindows()
            
            # Make sure window closes on OSx
            for i in range (1,5):
                cv2.waitKey(1)
            return
        
        # Read next frame
        time.sleep(0.05)             # control framerate for computation - default 20 frames per sec
        rval, frame = vc.read()    

# Call the laptop camera face/eye detector function above
laptop_camera_go()

---

Step 2: De-noise an Image for Better Face Detection

Image quality is an important aspect of any computer vision task. Typically, when creating a set of images to train a deep learning network, significant care is taken to ensure that training images are free of visual noise or artifacts that hinder object detection. While computer vision algorithms - like a face detector - are typically trained on 'nice' data such as this, new test data doesn't always look so nice!

When applying a trained computer vision algorithm to a new piece of test data one often cleans it up first before feeding it in. This sort of cleaning - referred to as pre-processing - can include a number of cleaning phases like blurring, de-noising, color transformations, etc., and many of these tasks can be accomplished using OpenCV.

In this short subsection we explore OpenCV's noise-removal functionality to see how we can clean up a noisy image, which we then feed into our trained face detector.

Create a noisy image to work with

In the next cell, we create an artificial noisy version of the previous multi-face image. This is a little exaggerated - we don't typically get images that are this noisy - but image noise, or 'grainy-ness' in a digitial image - is a fairly common phenomenon.

# Load in the multi-face test image again
image = cv2.imread('images/test_image_1.jpg')

# Convert the image copy to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Make an array copy of this image
image_with_noise = np.asarray(image) # Convert the input to an array

# Create noise - here we add noise sampled randomly from a Gaussian distribution: a common model for noise
noise_level = 40
noise = np.random.randn(image.shape[0],image.shape[1],image.shape[2])*noise_level

# Add this noise to the array image copy
image_with_noise = image_with_noise + noise

# Convert back to uint8 format
image_with_noise = np.asarray([np.uint8(np.clip(i,0,255)) for i in image_with_noise])

# Plot our noisy image!
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Noisy Image')
ax1.imshow(image_with_noise)

<matplotlib.image.AxesImage at 0x7fd95c7526d8>

In the context of face detection, the problem with an image like this is that - due to noise - we may miss some faces or get false detections.

In the next cell we apply the same trained OpenCV detector with the same settings as before, to see what sort of detections we get.

def detect_faces(img, scale_factor, min_neighbors):
    """
    Given an image img, return a numpy array of detected faces where each row is a detected face. 
    Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. 
    The first two entries in the array x, y specify the horizontal and vertical positions of the top left corner 
    The last two entries in the array w, h specify the width and height of the box.
    
    :param img: loaded image
    :scale_factor: float param to specify how much the image size is reduced at each image scale.
    :min_neighbors: int param to set how many neighbors each candidate rectangle should have to retain it.
    :return: 1D numpy array with the faces points detected
    """
        
    # Convert the RGB  image to grayscale
    gray_noise = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

    # Extract the pre-trained face detector from an xml file
    face_cascade = cv2.CascadeClassifier('detector_architectures/haarcascade_frontalface_default.xml')

    # Detect the faces in image
    faces = face_cascade.detectMultiScale(gray_noise, scale_factor, min_neighbors)

    # Print the number of faces detected in the image
    print('Number of faces detected:', len(faces))
    
    return faces

# Get the coordinates and dimension of faces on the image    
faces = detect_faces(image_with_noise, 4, 6) 

# Make a copy of the orginal image to draw face detections on
image_with_detections = np.copy(image_with_noise)

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 3)
    

# Display the image with the detections
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Noisy Image with Face Detections')
ax1.imshow(image_with_detections)

Number of faces detected: 12

<matplotlib.image.AxesImage at 0x7fd95c72c898>

With this added noise we now miss one of the faces!

(IMPLEMENTATION) De-noise this image for better face detection

Time to get your hands dirty: using OpenCV's built in color image de-noising functionality called fastNlMeansDenoisingColored - de-noise this image enough so that all the faces in the image are properly detected. Once you have cleaned the image in the next cell, use the cell that follows to run our trained face detector over the cleaned image to check out its detections.

You can find its official documentation here and a useful example here.

Note: you can keep all parameters except photo_render fixed as shown in the second link above. Play around with the value of this parameter - see how it affects the resulting cleaned image.

## TODO: Use OpenCV's built in color image de-noising function to clean up our noisy image!
denoised_image = cv2.fastNlMeansDenoisingColored(image,None,10,10,7,21) # your final de-noised image (should be RGB)

fig = plt.figure(figsize = (15,15))
ax = fig.add_subplot(121)
ax.set_title("Original Image")
ax.imshow(image)

ax = fig.add_subplot(122)
ax.set_title("Denoised Image")
ax.imshow(denoised_image)

<matplotlib.image.AxesImage at 0x7fd95c6417f0>

## TODO: Run the face detector on the de-noised image to improve your detections and display the result

# Get the coordinates and dimension of faces using the denoised image  
faces = detect_faces(denoised_image, 4, 6) 

# Make a copy of the orginal image to draw face detections on
image_with_detections = np.copy(image_with_noise)

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 3)
    

# Display the noisy image with the detections got from the denoised image
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Noisy Image with Face Detections')
ax1.imshow(image_with_detections)

Number of faces detected: 13

<matplotlib.image.AxesImage at 0x7fd95c589278>

---

Step 3: Blur an Image and Perform Edge Detection

Now that we have developed a simple pipeline for detecting faces using OpenCV - let's start playing around with a few fun things we can do with all those detected faces!

Importance of Blur in Edge Detection

Edge detection is a concept that pops up almost everywhere in computer vision applications, as edge-based features (as well as features built on top of edges) are often some of the best features for e.g., object detection and recognition problems.

Edge detection is a dimension reduction technique - by keeping only the edges of an image we get to throw away a lot of non-discriminating information. And typically the most useful kind of edge-detection is one that preserves only the important, global structures (ignoring local structures that aren't very discriminative). So removing local structures / retaining global structures is a crucial pre-processing step to performing edge detection in an image, and blurring can do just that.

Below is an animated gif showing the result of an edge-detected cat taken from Wikipedia, where the image is gradually blurred more and more prior to edge detection. When the animation begins you can't quite make out what it's a picture of, but as the animation evolves and local structures are removed via blurring the cat becomes visible in the edge-detected image.

Edge detection is a convolution performed on the image itself, and you can read about Canny edge detection on this OpenCV documentation page.

Canny edge detection

In the cell below we load in a test image, then apply Canny edge detection on it. The original image is shown on the left panel of the figure, while the edge-detected version of the image is shown on the right. Notice how the result looks very busy - there are too many little details preserved in the image before it is sent to the edge detector. When applied in computer vision applications, edge detection should preserve global structure; doing away with local structures that don't help describe what objects are in the image.

# Load in the image
image = cv2.imread('images/fawzia.jpg')

# Convert to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)  

# Perform Canny edge detection
canny_edges = cv2.Canny(gray,100,200)

# Dilate the image to amplify edges
dilated_edges = cv2.dilate(canny_edges, None)

# Plot the RGB and edge-detected image
fig = plt.figure(figsize = (15,15))
ax1 = fig.add_subplot(131)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Original Image')
ax1.imshow(image)

ax2 = fig.add_subplot(132)
ax2.set_xticks([])
ax2.set_yticks([])

ax2.set_title('Canny Edges')
ax2.imshow(canny_edges, cmap='gray')

ax2 = fig.add_subplot(133)
ax2.set_xticks([])
ax2.set_yticks([])

ax2.set_title('Dilated Edges')
ax2.imshow(dilated_edges, cmap='gray')

<matplotlib.image.AxesImage at 0x7fd95c4c9198>

Without first blurring the image, and removing small, local structures, a lot of irrelevant edge content gets picked up and amplified by the detector (as shown in the right panel above).

(IMPLEMENTATION) Blur the image then perform edge detection

In the next cell, you will repeat this experiment - blurring the image first to remove these local structures, so that only the important boudnary details remain in the edge-detected image.

Blur the image by using OpenCV's filter2d functionality - which is discussed in this documentation page - and use an averaging kernel of width equal to 4.

### TODO: Blur the test imageusing OpenCV's filter2d functionality, 
# Use an averaging kernel, and a kernel width equal to 4
     
kernel = 4
blur = cv2.filter2D(image,-1,kernel)

plt.subplot(121),plt.imshow(image),plt.title('Original')
plt.xticks([]), plt.yticks([])

plt.subplot(122),plt.imshow(blur),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()

## TODO: Then perform Canny edge detection and display the output

# Convert to grayscale
gray = cv2.cvtColor(blur, cv2.COLOR_RGB2GRAY)  

# Perform Canny edge detection
canny_edges = cv2.Canny(gray,100,200)

# Dilate the image to amplify edges
dilated_edges = cv2.dilate(canny_edges, None)

# Plot the RGB and edge-detected image
fig = plt.figure(figsize = (15,15))
ax1 = fig.add_subplot(131)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Original Image')
ax1.imshow(image)

ax2 = fig.add_subplot(132)
ax2.set_xticks([])
ax2.set_yticks([])

ax2.set_title('Canny Edges')
ax2.imshow(canny_edges, cmap='gray')

ax2 = fig.add_subplot(133)
ax2.set_xticks([])
ax2.set_yticks([])

ax2.set_title('Dilated Edges')
ax2.imshow(dilated_edges, cmap='gray')

<matplotlib.image.AxesImage at 0x7fd95c37ae80>

---

Step 4: Automatically Hide the Identity of an Individual

If you film something like a documentary or reality TV, you must get permission from every individual shown on film before you can show their face, otherwise you need to blur it out - by blurring the face a lot (so much so that even the global structures are obscured)! This is also true for projects like Google's StreetView maps - an enormous collection of mapping images taken from a fleet of Google vehicles. Because it would be impossible for Google to get the permission of every single person accidentally captured in one of these images they blur out everyone's faces, the detected images must automatically blur the identity of detected people. Here's a few examples of folks caught in the camera of a Google street view vehicle.

Read in an image to perform identity detection

Let's try this out for ourselves. Use the face detection pipeline built above and what you know about using the filter2D to blur and image, and use these in tandem to hide the identity of the person in the following image - loaded in and printed in the next cell.

# Load in the image
image = cv2.imread('images/gus.jpg')

# Convert the image to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Display the image
fig = plt.figure(figsize = (6,6))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])
ax1.set_title('Original Image')
ax1.imshow(image)

<matplotlib.image.AxesImage at 0x7fd95c299b38>

(IMPLEMENTATION) Use blurring to hide the identity of an individual in an image

The idea here is to 1) automatically detect the face in this image, and then 2) blur it out! Make sure to adjust the parameters of the averaging blur filter to completely obscure this person's identity.

## TODO: Implement face detection

faces = detect_faces(image, 1.4, 3)

# Make a copy of the orginal image to draw face detections on
image_with_detections = np.copy(image)

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 3)
    
# Display the noisy image with the detections got from the denoised image
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with Face Detections')
ax1.imshow(image_with_detections)    

Number of faces detected: 1

<matplotlib.image.AxesImage at 0x7fd95c273b38>

## TODO: Blur the bounding box around each detected face using an averaging filter and display the result

# Get the bounding box for each detected face
for (x,y,w,h) in faces:
    # Add a red bounding box to the detections image
    image_with_detections[y:y+h, x:x+w] = cv2.blur(image_with_detections[y:y+h, x:x+w] ,(100,100))
    cv2.rectangle(image_with_detections, (x,y), (x+w,y+h), (255,0,0), 3)
    
# Display the noisy image with the detections got from the denoised image
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with face detection + blurring')
ax1.imshow(image_with_detections) 

<matplotlib.image.AxesImage at 0x7fd95c1cad30>

(Optional) Build identity protection into your laptop camera

In this optional task you can add identity protection to your laptop camera, using the previously completed code where you added face detection to your laptop camera - and the task above. You should be able to get reasonable results with little parameter tuning - like the one shown in the gif below.

As with the previous video task, to make this perfect would require significant effort - so don't strive for perfection here, strive for reasonable quality.

The next cell contains code a wrapper function called laptop_camera_identity_hider that - when called - will activate your laptop's camera. You need to place the relevant face detection and blurring code developed above in this function in order to blur faces entering your laptop camera's field of view.

Before adding anything to the function you can call it to get a hang of how it works - a small window will pop up showing you the live feed from your camera, you can press any key to close this window.

Note: Mac users may find that activating this function kills the kernel of their notebook every once in a while. If this happens to you, just restart your notebook's kernel, activate cell(s) containing any crucial import statements, and you'll be good to go!

### Insert face detection and blurring code into the wrapper below to create an identity protector on your laptop!
import cv2
import time 

def laptop_camera_go():
    # Create instance of video capturer
    cv2.namedWindow("face detection activated")
    vc = cv2.VideoCapture(0)

    # Try to get the first frame
    if vc.isOpened(): 
        rval, frame = vc.read()
    else:
        rval = False
    
    # Keep video stream open
    while rval:
        # Plot image from camera with detections marked
        cv2.imshow("face detection activated", frame)
        
        # Exit functionality - press any key to exit laptop video
        key = cv2.waitKey(20)
        if key > 0: # Exit by pressing any key
            # Destroy windows
            cv2.destroyAllWindows()
            
            for i in range (1,5):
                cv2.waitKey(1)
            return
        
        # Read next frame
        time.sleep(0.05)             # control framerate for computation - default 20 frames per sec
        rval, frame = vc.read()    
        

# Run laptop identity hider
laptop_camera_go()

---

Step 5: Create a CNN to Recognize Facial Keypoints

OpenCV is often used in practice with other machine learning and deep learning libraries to produce interesting results. In this stage of the project you will create your own end-to-end pipeline - employing convolutional networks in keras along with OpenCV - to apply a "selfie" filter to streaming video and images.

You will start by creating and then training a convolutional network that can detect facial keypoints in a small dataset of cropped images of human faces. We then guide you towards OpenCV to expanding your detection algorithm to more general images. What are facial keypoints? Let's take a look at some examples.

Facial keypoints (also called facial landmarks) are the small blue-green dots shown on each of the faces in the image above - there are 15 keypoints marked in each image. They mark important areas of the face - the eyes, corners of the mouth, the nose, etc. Facial keypoints can be used in a variety of machine learning applications from face and emotion recognition to commercial applications like the image filters popularized by Snapchat.

Below we illustrate a filter that, using the results of this section, automatically places sunglasses on people in images (using the facial keypoints to place the glasses correctly on each face). Here, the facial keypoints have been colored lime green for visualization purposes.

Make a facial keypoint detector

But first things first: how can we make a facial keypoint detector? Well, at a high level, notice that facial keypoint detection is a regression problem. A single face corresponds to a set of 15 facial keypoints (a set of 15 corresponding $(x, y)$ coordinates, i.e., an output point). Because our input data are images, we can employ a convolutional neural network to recognize patterns in our images and learn how to identify these keypoint given sets of labeled data.

In order to train a regressor, we need a training set - a set of facial image / facial keypoint pairs to train on. For this we will be using this dataset from Kaggle. We've already downloaded this data and placed it in the data directory. Make sure that you have both the training and test data files. The training dataset contains several thousand $96 \times 96$ grayscale images of cropped human faces, along with each face's 15 corresponding facial keypoints (also called landmarks) that have been placed by hand, and recorded in $(x, y)$ coordinates. This wonderful resource also has a substantial testing set, which we will use in tinkering with our convolutional network.

To load in this data, run the Python cell below - notice we will load in both the training and testing sets.

The load_data function is in the included utils.py file.

from utils import *

# Load training set
X_train, y_train = load_data()
print("X_train.shape == {}".format(X_train.shape))
print("y_train.shape == {}; y_train.min == {:.3f}; y_train.max == {:.3f}".format(
    y_train.shape, y_train.min(), y_train.max()))

# Load testing set
X_test, _ = load_data(test=True) # no y_test since y_test will be the predicted y, once we run the model. 
print("X_test.shape == {}".format(X_test.shape))

Using TensorFlow backend.

X_train.shape == (2140, 96, 96, 1)
y_train.shape == (2140, 30); y_train.min == -0.920; y_train.max == 0.996
X_test.shape == (1783, 96, 96, 1)

The load_data function in utils.py originates from this excellent blog post, which you are strongly encouraged to read. Please take the time now to review this function. Note how the output values - that is, the coordinates of each set of facial landmarks - have been normalized to take on values in the range $[-1, 1]$, while the pixel values of each input point (a facial image) have been normalized to the range $[0,1]$.

Note: the original Kaggle dataset contains some images with several missing keypoints. For simplicity, the load_data function removes those images with missing labels from the dataset. As an optional extension, you are welcome to amend the load_data function to include the incomplete data points.

Visualize the Training Data

Execute the code cell below to visualize a subset of the training data.

import matplotlib.pyplot as plt
%matplotlib inline

fig = plt.figure(figsize=(20,20))
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)
for i in range(9):
    ax = fig.add_subplot(3, 3, i + 1, xticks=[], yticks=[])
    plot_data(X_train[i], y_train[i], ax)

For each training image, there are two landmarks per eyebrow (four total), three per eye (six total), four for the mouth, and one for the tip of the nose.

Review the plot_data function in utils.py to understand how the 30-dimensional training labels in y_train are mapped to facial locations, as this function will prove useful for your pipeline.

(IMPLEMENTATION) Specify the CNN Architecture

In this section, you will specify a neural network for predicting the locations of facial keypoints. Use the code cell below to specify the architecture of your neural network. We have imported some layers that you may find useful for this task, but if you need to use more Keras layers, feel free to import them in the cell.

Your network should accept a $96 \times 96$ grayscale image as input, and it should output a vector with 30 entries, corresponding to the predicted (horizontal and vertical) locations of 15 facial keypoints. If you are not sure where to start, you can find some useful starting architectures in this blog, but you are not permitted to copy any of the architectures that you find online.

# Import deep learning resources from Keras
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D, Dropout, GlobalAveragePooling2D
from keras.layers import Flatten, Dense, Activation
from keras.layers.normalization import BatchNormalization
from keras.callbacks import EarlyStopping
from keras.initializers import RandomNormal
from keras.backend import clear_session

## TODO: Specify a CNN architecture
# Your model should accept 96x96 pixel graysale images in
# It should have a fully-connected output layer with 30 values (2 for each facial keypoint)

clear_session()

model = Sequential()

w_init = RandomNormal(mean=0.0, stddev=0.02, seed=None)

### Define your architecture.

model.add(Convolution2D(filters=32, kernel_size=3, padding='valid', input_shape=(96, 96, 1), kernel_initializer=w_init))
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.3))

model.add(Convolution2D(filters=64, kernel_size=2, padding='valid'))
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Convolution2D(filters=128, kernel_size=2, padding='valid'))
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Convolution2D(filters=256, kernel_size=2, padding='valid'))
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Convolution2D(filters=512, kernel_size=2, padding='valid'))
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(GlobalAveragePooling2D()) 
# model.add(Dense(500, kernel_initializer=w_init))
# model.add(Dropout(0.2))
model.add(Dense(30)) # There are 15 points --> (x, y) 30 coordinates

# Summarize the model
model.summary()

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 94, 94, 32)        320       
_________________________________________________________________
activation_1 (Activation)    (None, 94, 94, 32)        0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 47, 47, 32)        0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 47, 47, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 46, 46, 64)        8256      
_________________________________________________________________
activation_2 (Activation)    (None, 46, 46, 64)        0         
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 23, 23, 64)        0         
_________________________________________________________________
dropout_2 (Dropout)          (None, 23, 23, 64)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 22, 22, 128)       32896     
_________________________________________________________________
activation_3 (Activation)    (None, 22, 22, 128)       0         
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 11, 11, 128)       0         
_________________________________________________________________
dropout_3 (Dropout)          (None, 11, 11, 128)       0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 10, 10, 256)       131328    
_________________________________________________________________
activation_4 (Activation)    (None, 10, 10, 256)       0         
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 5, 5, 256)         0         
_________________________________________________________________
dropout_4 (Dropout)          (None, 5, 5, 256)         0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 4, 4, 512)         524800    
_________________________________________________________________
activation_5 (Activation)    (None, 4, 4, 512)         0         
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 2, 2, 512)         0         
_________________________________________________________________
dropout_5 (Dropout)          (None, 2, 2, 512)         0         
_________________________________________________________________
global_average_pooling2d_1 ( (None, 512)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 30)                15390     
=================================================================
Total params: 712,990
Trainable params: 712,990
Non-trainable params: 0
_________________________________________________________________

---

Step 6: Compile and Train the Model

After specifying your architecture, you'll need to compile and train the model to detect facial keypoints'

(IMPLEMENTATION) Compile and Train the Model

Use the compile method to configure the learning process. Experiment with your choice of optimizer; you may have some ideas about which will work best (SGD vs. RMSprop, etc), but take the time to empirically verify your theories.

Use the fit method to train the model. Break off a validation set by setting validation_split=0.2. Save the returned History object in the history variable.

Experiment with your model to minimize the validation loss (measured as mean squared error). A very good model will achieve about 0.0015 loss (though it's possible to do even better). When you have finished training, save your model as an HDF5 file with file path my_model.h5.

from keras.optimizers import SGD, RMSprop, Adagrad, Adadelta, Adam, Adamax, Nadam
from keras.callbacks import ModelCheckpoint 

## TODO: Compile the model

# opt = Nadam(lr=0.0001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, schedule_decay=0.004)
# opt = SGD(lr=0.0015, momentum=0.9, nesterov=True)
# opt = Adamax(lr=0.0010) 
# opt = RMSprop(lr=0.001)
# opt = Adam(lr=0.0001, decay=0.0005)

model.compile(loss="mean_squared_error", optimizer='Adamax', metrics=['accuracy'])

# Define Callbacks
early_stopping = EarlyStopping(monitor='val_loss', mode='auto', patience=100)

# Saving the best model
checkpointer = ModelCheckpoint(filepath='model.h5', 
                               verbose=1, save_best_only=True)

## TODO: Train the model
hist = model.fit(X_train, y_train, batch_size=256, epochs=1200, verbose=1, 
                 validation_split=0.2, callbacks=[checkpointer, early_stopping])

Train on 1712 samples, validate on 428 samples
Epoch 1/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0657 - acc: 0.1686Epoch 00000: val_loss improved from inf to 0.07718, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0605 - acc: 0.2249 - val_loss: 0.0772 - val_acc: 0.6963
Epoch 2/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0174 - acc: 0.7083Epoch 00001: val_loss improved from 0.07718 to 0.04529, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0167 - acc: 0.7050 - val_loss: 0.0453 - val_acc: 0.6963
Epoch 3/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0091 - acc: 0.6178Epoch 00002: val_loss improved from 0.04529 to 0.03657, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0091 - acc: 0.6063 - val_loss: 0.0366 - val_acc: 0.6963
Epoch 4/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0081 - acc: 0.6608Epoch 00003: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0079 - acc: 0.6676 - val_loss: 0.0371 - val_acc: 0.6963
Epoch 5/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0063 - acc: 0.7064Epoch 00004: val_loss improved from 0.03657 to 0.03386, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0062 - acc: 0.7050 - val_loss: 0.0339 - val_acc: 0.6963
Epoch 6/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0056 - acc: 0.7031Epoch 00005: val_loss improved from 0.03386 to 0.02934, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0056 - acc: 0.7062 - val_loss: 0.0293 - val_acc: 0.6963
Epoch 7/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0052 - acc: 0.7044Epoch 00006: val_loss improved from 0.02934 to 0.02865, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0052 - acc: 0.7039 - val_loss: 0.0286 - val_acc: 0.6963
Epoch 8/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0050 - acc: 0.6999Epoch 00007: val_loss improved from 0.02865 to 0.02764, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0050 - acc: 0.7039 - val_loss: 0.0276 - val_acc: 0.6963
Epoch 9/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7025Epoch 00008: val_loss improved from 0.02764 to 0.02678, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0049 - acc: 0.7050 - val_loss: 0.0268 - val_acc: 0.6963
Epoch 10/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7051Epoch 00009: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7027 - val_loss: 0.0272 - val_acc: 0.6963
Epoch 11/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7070Epoch 00010: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0049 - acc: 0.7033 - val_loss: 0.0274 - val_acc: 0.6963
Epoch 12/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7077Epoch 00011: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0049 - acc: 0.7062 - val_loss: 0.0280 - val_acc: 0.6963
Epoch 13/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7031Epoch 00012: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7044 - val_loss: 0.0277 - val_acc: 0.6963
Epoch 14/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7031Epoch 00013: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7062 - val_loss: 0.0276 - val_acc: 0.6963
Epoch 15/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7031Epoch 00014: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7039 - val_loss: 0.0280 - val_acc: 0.6963
Epoch 16/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7031Epoch 00015: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7050 - val_loss: 0.0282 - val_acc: 0.6963
Epoch 17/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7038Epoch 00016: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7039 - val_loss: 0.0282 - val_acc: 0.6963
Epoch 18/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7090Epoch 00017: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7062 - val_loss: 0.0276 - val_acc: 0.6963
Epoch 19/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7057Epoch 00018: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7056 - val_loss: 0.0279 - val_acc: 0.6963
Epoch 20/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7057Epoch 00019: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7056 - val_loss: 0.0269 - val_acc: 0.6963
Epoch 21/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0049 - acc: 0.7018Epoch 00020: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7033 - val_loss: 0.0272 - val_acc: 0.6963
Epoch 22/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7096Epoch 00021: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7056 - val_loss: 0.0273 - val_acc: 0.6963
Epoch 23/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7064Epoch 00022: val_loss improved from 0.02678 to 0.02652, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7050 - val_loss: 0.0265 - val_acc: 0.6963
Epoch 24/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7103Epoch 00023: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7062 - val_loss: 0.0274 - val_acc: 0.6963
Epoch 25/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7057Epoch 00024: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7039 - val_loss: 0.0282 - val_acc: 0.6963
Epoch 26/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7018Epoch 00025: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7062 - val_loss: 0.0273 - val_acc: 0.6963
Epoch 27/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00026: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0048 - acc: 0.7062 - val_loss: 0.0268 - val_acc: 0.6963
Epoch 28/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00027: val_loss improved from 0.02652 to 0.02619, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7050 - val_loss: 0.0262 - val_acc: 0.6963
Epoch 29/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7012Epoch 00028: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7044 - val_loss: 0.0268 - val_acc: 0.6963
Epoch 30/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7064Epoch 00029: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7079 - val_loss: 0.0270 - val_acc: 0.6963
Epoch 31/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7064Epoch 00030: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7050 - val_loss: 0.0265 - val_acc: 0.6963
Epoch 32/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7070Epoch 00031: val_loss improved from 0.02619 to 0.02593, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7074 - val_loss: 0.0259 - val_acc: 0.6963
Epoch 33/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7057Epoch 00032: val_loss improved from 0.02593 to 0.02589, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7068 - val_loss: 0.0259 - val_acc: 0.6963
Epoch 34/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7051Epoch 00033: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7062 - val_loss: 0.0259 - val_acc: 0.6963
Epoch 35/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7025Epoch 00034: val_loss improved from 0.02589 to 0.02572, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7056 - val_loss: 0.0257 - val_acc: 0.6963
Epoch 36/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7005Epoch 00035: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7085 - val_loss: 0.0262 - val_acc: 0.6963
Epoch 37/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7188Epoch 00036: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7074 - val_loss: 0.0263 - val_acc: 0.6963
Epoch 38/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7096Epoch 00037: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7050 - val_loss: 0.0262 - val_acc: 0.6963
Epoch 39/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00038: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7062 - val_loss: 0.0257 - val_acc: 0.6963
Epoch 40/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7077Epoch 00039: val_loss improved from 0.02572 to 0.02481, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7068 - val_loss: 0.0248 - val_acc: 0.6963
Epoch 41/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00040: val_loss improved from 0.02481 to 0.02421, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7050 - val_loss: 0.0242 - val_acc: 0.6963
Epoch 42/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.6999Epoch 00041: val_loss improved from 0.02421 to 0.02383, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7044 - val_loss: 0.0238 - val_acc: 0.6963
Epoch 43/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7064Epoch 00042: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7062 - val_loss: 0.0244 - val_acc: 0.6963
Epoch 44/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7083Epoch 00043: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7079 - val_loss: 0.0248 - val_acc: 0.6963
Epoch 45/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7103Epoch 00044: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7044 - val_loss: 0.0246 - val_acc: 0.6963
Epoch 46/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00045: val_loss improved from 0.02383 to 0.02361, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0236 - val_acc: 0.6963
Epoch 47/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7103Epoch 00046: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7074 - val_loss: 0.0237 - val_acc: 0.6963
Epoch 48/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7057Epoch 00047: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7056 - val_loss: 0.0239 - val_acc: 0.6963
Epoch 49/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7142Epoch 00048: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7079 - val_loss: 0.0240 - val_acc: 0.6963
Epoch 50/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7005Epoch 00049: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7062 - val_loss: 0.0237 - val_acc: 0.6963
Epoch 51/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7090Epoch 00050: val_loss improved from 0.02361 to 0.02250, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0225 - val_acc: 0.6963
Epoch 52/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7057Epoch 00051: val_loss improved from 0.02250 to 0.02235, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0223 - val_acc: 0.6963
Epoch 53/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7077Epoch 00052: val_loss improved from 0.02235 to 0.02188, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0219 - val_acc: 0.6963
Epoch 54/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7051Epoch 00053: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7062 - val_loss: 0.0219 - val_acc: 0.6963
Epoch 55/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7038Epoch 00054: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7027 - val_loss: 0.0226 - val_acc: 0.6963
Epoch 56/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0048 - acc: 0.7012Epoch 00055: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7074 - val_loss: 0.0225 - val_acc: 0.6963
Epoch 57/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7135Epoch 00056: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0221 - val_acc: 0.6963
Epoch 58/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7038Epoch 00057: val_loss improved from 0.02188 to 0.02169, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0217 - val_acc: 0.6963
Epoch 59/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7025Epoch 00058: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0222 - val_acc: 0.6963
Epoch 60/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7031Epoch 00059: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0047 - acc: 0.7050 - val_loss: 0.0230 - val_acc: 0.6963
Epoch 61/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7109Epoch 00060: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7091 - val_loss: 0.0226 - val_acc: 0.6963
Epoch 62/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7057Epoch 00061: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0222 - val_acc: 0.6963
Epoch 63/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7057Epoch 00062: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7079 - val_loss: 0.0219 - val_acc: 0.6963
Epoch 64/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7161Epoch 00063: val_loss improved from 0.02169 to 0.02133, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0213 - val_acc: 0.6963
Epoch 65/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7057Epoch 00064: val_loss improved from 0.02133 to 0.02125, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0212 - val_acc: 0.6963
Epoch 66/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7090Epoch 00065: val_loss improved from 0.02125 to 0.02053, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0205 - val_acc: 0.6963
Epoch 67/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0047 - acc: 0.7103Epoch 00066: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0218 - val_acc: 0.6963
Epoch 68/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7044Epoch 00067: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7056 - val_loss: 0.0221 - val_acc: 0.6963
Epoch 69/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7031Epoch 00068: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0217 - val_acc: 0.6963
Epoch 70/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7077Epoch 00069: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7050 - val_loss: 0.0217 - val_acc: 0.6963
Epoch 71/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7096Epoch 00070: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0207 - val_acc: 0.6963
Epoch 72/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7025Epoch 00071: val_loss improved from 0.02053 to 0.02005, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7044 - val_loss: 0.0201 - val_acc: 0.6963
Epoch 73/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7057Epoch 00072: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0202 - val_acc: 0.6963
Epoch 74/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7044Epoch 00073: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0202 - val_acc: 0.6963
Epoch 75/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7044Epoch 00074: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7079 - val_loss: 0.0212 - val_acc: 0.6963
Epoch 76/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7077Epoch 00075: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0206 - val_acc: 0.6963
Epoch 77/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7122Epoch 00076: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0204 - val_acc: 0.6963
Epoch 78/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7109Epoch 00077: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0211 - val_acc: 0.6963
Epoch 79/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7031Epoch 00078: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7056 - val_loss: 0.0205 - val_acc: 0.6963
Epoch 80/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7090Epoch 00079: val_loss improved from 0.02005 to 0.01934, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0193 - val_acc: 0.6963
Epoch 81/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7051Epoch 00080: val_loss improved from 0.01934 to 0.01912, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0191 - val_acc: 0.6963
Epoch 82/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7083Epoch 00081: val_loss improved from 0.01912 to 0.01857, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7074 - val_loss: 0.0186 - val_acc: 0.6963
Epoch 83/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7077Epoch 00082: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0191 - val_acc: 0.6963
Epoch 84/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7051Epoch 00083: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7062 - val_loss: 0.0203 - val_acc: 0.6963
Epoch 85/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7038Epoch 00084: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7079 - val_loss: 0.0205 - val_acc: 0.6963
Epoch 86/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7070Epoch 00085: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0196 - val_acc: 0.6963
Epoch 87/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7044Epoch 00086: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7062 - val_loss: 0.0189 - val_acc: 0.6963
Epoch 88/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7077Epoch 00087: val_loss improved from 0.01857 to 0.01824, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7079 - val_loss: 0.0182 - val_acc: 0.6963
Epoch 89/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7148Epoch 00088: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7062 - val_loss: 0.0189 - val_acc: 0.6963
Epoch 90/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7070Epoch 00089: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7056 - val_loss: 0.0191 - val_acc: 0.6963
Epoch 91/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7057Epoch 00090: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7056 - val_loss: 0.0186 - val_acc: 0.6963
Epoch 92/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7116Epoch 00091: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0187 - val_acc: 0.6963
Epoch 93/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7070Epoch 00092: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7056 - val_loss: 0.0204 - val_acc: 0.6963
Epoch 94/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7044Epoch 00093: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0212 - val_acc: 0.6963
Epoch 95/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.6999Epoch 00094: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0046 - acc: 0.7068 - val_loss: 0.0205 - val_acc: 0.6963
Epoch 96/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7070Epoch 00095: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0200 - val_acc: 0.6963
Epoch 97/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7057Epoch 00096: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0183 - val_acc: 0.6963
Epoch 98/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7090Epoch 00097: val_loss improved from 0.01824 to 0.01790, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0179 - val_acc: 0.6963
Epoch 99/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7103Epoch 00098: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0183 - val_acc: 0.6963
Epoch 100/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7064Epoch 00099: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0198 - val_acc: 0.6963
Epoch 101/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7070Epoch 00100: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0189 - val_acc: 0.6963
Epoch 102/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7025Epoch 00101: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7062 - val_loss: 0.0183 - val_acc: 0.6963
Epoch 103/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7116Epoch 00102: val_loss improved from 0.01790 to 0.01762, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7062 - val_loss: 0.0176 - val_acc: 0.6963
Epoch 104/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7090Epoch 00103: val_loss improved from 0.01762 to 0.01705, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0170 - val_acc: 0.6963
Epoch 105/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7064Epoch 00104: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0173 - val_acc: 0.6963
Epoch 106/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7142Epoch 00105: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7079 - val_loss: 0.0184 - val_acc: 0.6963
Epoch 107/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7077Epoch 00106: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0184 - val_acc: 0.6963
Epoch 108/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7031Epoch 00107: val_loss improved from 0.01705 to 0.01669, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0167 - val_acc: 0.6963
Epoch 109/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7083Epoch 00108: val_loss improved from 0.01669 to 0.01630, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7068 - val_loss: 0.0163 - val_acc: 0.6963
Epoch 110/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7103Epoch 00109: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0175 - val_acc: 0.6963
Epoch 111/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7057Epoch 00110: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0192 - val_acc: 0.6963
Epoch 112/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7155Epoch 00111: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0193 - val_acc: 0.6963
Epoch 113/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7096Epoch 00112: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7079 - val_loss: 0.0180 - val_acc: 0.6963
Epoch 114/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7070Epoch 00113: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7079 - val_loss: 0.0178 - val_acc: 0.6963
Epoch 115/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0046 - acc: 0.7129Epoch 00114: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0163 - val_acc: 0.6963
Epoch 116/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7038Epoch 00115: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0045 - acc: 0.7074 - val_loss: 0.0169 - val_acc: 0.6963
Epoch 117/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7090Epoch 00116: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7079 - val_loss: 0.0171 - val_acc: 0.6963
Epoch 118/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7083Epoch 00117: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0173 - val_acc: 0.6963
Epoch 119/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7038Epoch 00118: val_loss improved from 0.01630 to 0.01603, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7050 - val_loss: 0.0160 - val_acc: 0.6963
Epoch 120/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0045 - acc: 0.7031Epoch 00119: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7068 - val_loss: 0.0164 - val_acc: 0.6963
Epoch 121/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7044Epoch 00120: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7062 - val_loss: 0.0161 - val_acc: 0.6963
Epoch 122/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7051Epoch 00121: val_loss improved from 0.01603 to 0.01564, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7079 - val_loss: 0.0156 - val_acc: 0.6963
Epoch 123/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7077Epoch 00122: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7062 - val_loss: 0.0161 - val_acc: 0.6963
Epoch 124/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7090Epoch 00123: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7068 - val_loss: 0.0159 - val_acc: 0.6963
Epoch 125/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7051Epoch 00124: val_loss improved from 0.01564 to 0.01532, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0153 - val_acc: 0.6963
Epoch 126/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7103Epoch 00125: val_loss improved from 0.01532 to 0.01528, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0153 - val_acc: 0.6963
Epoch 127/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7005Epoch 00126: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0157 - val_acc: 0.6963
Epoch 128/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7057Epoch 00127: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7079 - val_loss: 0.0156 - val_acc: 0.6963
Epoch 129/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7103Epoch 00128: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0154 - val_acc: 0.6963
Epoch 130/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7044Epoch 00129: val_loss improved from 0.01528 to 0.01404, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7079 - val_loss: 0.0140 - val_acc: 0.6963
Epoch 131/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7077Epoch 00130: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0158 - val_acc: 0.6963
Epoch 132/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7096Epoch 00131: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7050 - val_loss: 0.0153 - val_acc: 0.6963
Epoch 133/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7025Epoch 00132: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0141 - val_acc: 0.6963
Epoch 134/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7031Epoch 00133: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7079 - val_loss: 0.0166 - val_acc: 0.6963
Epoch 135/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7077Epoch 00134: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0149 - val_acc: 0.6963
Epoch 136/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7129Epoch 00135: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7079 - val_loss: 0.0140 - val_acc: 0.6963
Epoch 137/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.6979Epoch 00136: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7079 - val_loss: 0.0158 - val_acc: 0.6963
Epoch 138/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.7129Epoch 00137: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0150 - val_acc: 0.6963
Epoch 139/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7031Epoch 00138: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7050 - val_loss: 0.0142 - val_acc: 0.6963
Epoch 140/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.6999Epoch 00139: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7074 - val_loss: 0.0155 - val_acc: 0.6963
Epoch 141/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7077Epoch 00140: val_loss improved from 0.01404 to 0.01396, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7050 - val_loss: 0.0140 - val_acc: 0.6963
Epoch 142/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7077Epoch 00141: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7074 - val_loss: 0.0150 - val_acc: 0.6963
Epoch 143/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0044 - acc: 0.6947Epoch 00142: val_loss improved from 0.01396 to 0.01383, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0044 - acc: 0.7027 - val_loss: 0.0138 - val_acc: 0.6963
Epoch 144/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7096Epoch 00143: val_loss improved from 0.01383 to 0.01359, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7074 - val_loss: 0.0136 - val_acc: 0.6963
Epoch 145/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7129Epoch 00144: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7068 - val_loss: 0.0148 - val_acc: 0.6963
Epoch 146/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7018Epoch 00145: val_loss improved from 0.01359 to 0.01345, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7074 - val_loss: 0.0134 - val_acc: 0.6963
Epoch 147/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.6999Epoch 00146: val_loss improved from 0.01345 to 0.01256, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7074 - val_loss: 0.0126 - val_acc: 0.6963
Epoch 148/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7064Epoch 00147: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7079 - val_loss: 0.0145 - val_acc: 0.6963
Epoch 149/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7064Epoch 00148: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7050 - val_loss: 0.0135 - val_acc: 0.6963
Epoch 150/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0043 - acc: 0.7083Epoch 00149: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0043 - acc: 0.7074 - val_loss: 0.0138 - val_acc: 0.6963
Epoch 151/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7012Epoch 00150: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7039 - val_loss: 0.0134 - val_acc: 0.6963
Epoch 152/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7051Epoch 00151: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7044 - val_loss: 0.0129 - val_acc: 0.6963
Epoch 153/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7051Epoch 00152: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7074 - val_loss: 0.0141 - val_acc: 0.6963
Epoch 154/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7070Epoch 00153: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7050 - val_loss: 0.0130 - val_acc: 0.6963
Epoch 155/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7083Epoch 00154: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7056 - val_loss: 0.0134 - val_acc: 0.6986
Epoch 156/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7018Epoch 00155: val_loss improved from 0.01256 to 0.01215, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7027 - val_loss: 0.0122 - val_acc: 0.6986
Epoch 157/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7025Epoch 00156: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7074 - val_loss: 0.0134 - val_acc: 0.6986
Epoch 158/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7005Epoch 00157: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7050 - val_loss: 0.0127 - val_acc: 0.6986
Epoch 159/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7064Epoch 00158: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7033 - val_loss: 0.0138 - val_acc: 0.7009
Epoch 160/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7031Epoch 00159: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7033 - val_loss: 0.0130 - val_acc: 0.6986
Epoch 161/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7109Epoch 00160: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7068 - val_loss: 0.0130 - val_acc: 0.7009
Epoch 162/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7064Epoch 00161: val_loss improved from 0.01215 to 0.01124, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7015 - val_loss: 0.0112 - val_acc: 0.6986
Epoch 163/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7070Epoch 00162: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7044 - val_loss: 0.0131 - val_acc: 0.6986
Epoch 164/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.6960Epoch 00163: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.6992 - val_loss: 0.0121 - val_acc: 0.6986
Epoch 165/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7083Epoch 00164: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7085 - val_loss: 0.0132 - val_acc: 0.7033
Epoch 166/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7038Epoch 00165: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0042 - acc: 0.7044 - val_loss: 0.0121 - val_acc: 0.6986
Epoch 167/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.6999Epoch 00166: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7039 - val_loss: 0.0125 - val_acc: 0.7009
Epoch 168/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7064Epoch 00167: val_loss improved from 0.01124 to 0.01099, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7074 - val_loss: 0.0110 - val_acc: 0.6986
Epoch 169/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.7103Epoch 00168: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7039 - val_loss: 0.0134 - val_acc: 0.7009
Epoch 170/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0042 - acc: 0.6999Epoch 00169: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7068 - val_loss: 0.0120 - val_acc: 0.6986
Epoch 171/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7038Epoch 00170: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7033 - val_loss: 0.0117 - val_acc: 0.7009
Epoch 172/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.6953Epoch 00171: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7021 - val_loss: 0.0114 - val_acc: 0.7009
Epoch 173/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7018Epoch 00172: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7027 - val_loss: 0.0118 - val_acc: 0.7009
Epoch 174/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7005Epoch 00173: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7068 - val_loss: 0.0116 - val_acc: 0.7009
Epoch 175/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7090Epoch 00174: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7009 - val_loss: 0.0122 - val_acc: 0.6986
Epoch 176/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7025Epoch 00175: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7027 - val_loss: 0.0118 - val_acc: 0.7009
Epoch 177/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7038Epoch 00176: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7033 - val_loss: 0.0118 - val_acc: 0.7009
Epoch 178/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.6979Epoch 00177: val_loss improved from 0.01099 to 0.00983, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7015 - val_loss: 0.0098 - val_acc: 0.6986
Epoch 179/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7096Epoch 00178: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7085 - val_loss: 0.0131 - val_acc: 0.6986
Epoch 180/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7038Epoch 00179: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7027 - val_loss: 0.0103 - val_acc: 0.6986
Epoch 181/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0041 - acc: 0.7096Epoch 00180: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0041 - acc: 0.7056 - val_loss: 0.0128 - val_acc: 0.7009
Epoch 182/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7083Epoch 00181: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7056 - val_loss: 0.0105 - val_acc: 0.6986
Epoch 183/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7018Epoch 00182: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7085 - val_loss: 0.0112 - val_acc: 0.7009
Epoch 184/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7122Epoch 00183: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7050 - val_loss: 0.0117 - val_acc: 0.6986
Epoch 185/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7044Epoch 00184: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7044 - val_loss: 0.0104 - val_acc: 0.7009
Epoch 186/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7070Epoch 00185: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7068 - val_loss: 0.0123 - val_acc: 0.6986
Epoch 187/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7116Epoch 00186: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7039 - val_loss: 0.0101 - val_acc: 0.6986
Epoch 188/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7090Epoch 00187: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7074 - val_loss: 0.0124 - val_acc: 0.6986
Epoch 189/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7031Epoch 00188: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7062 - val_loss: 0.0105 - val_acc: 0.7009
Epoch 190/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.6999Epoch 00189: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7044 - val_loss: 0.0103 - val_acc: 0.6963
Epoch 191/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7077Epoch 00190: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7068 - val_loss: 0.0101 - val_acc: 0.6986
Epoch 192/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7142Epoch 00191: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7085 - val_loss: 0.0104 - val_acc: 0.7009
Epoch 193/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7018Epoch 00192: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7044 - val_loss: 0.0102 - val_acc: 0.6986
Epoch 194/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7064Epoch 00193: val_loss improved from 0.00983 to 0.00904, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7050 - val_loss: 0.0090 - val_acc: 0.6986
Epoch 195/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7044Epoch 00194: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7033 - val_loss: 0.0116 - val_acc: 0.6986
Epoch 196/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7083Epoch 00195: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0040 - acc: 0.7074 - val_loss: 0.0098 - val_acc: 0.6986
Epoch 197/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7057Epoch 00196: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7062 - val_loss: 0.0104 - val_acc: 0.6986
Epoch 198/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7077Epoch 00197: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7062 - val_loss: 0.0098 - val_acc: 0.6986
Epoch 199/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7057Epoch 00198: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7050 - val_loss: 0.0105 - val_acc: 0.6986
Epoch 200/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7005Epoch 00199: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.6998 - val_loss: 0.0099 - val_acc: 0.6963
Epoch 201/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7070Epoch 00200: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7039 - val_loss: 0.0095 - val_acc: 0.6986
Epoch 202/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7012Epoch 00201: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.6998 - val_loss: 0.0104 - val_acc: 0.6986
Epoch 203/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0038 - acc: 0.7096Epoch 00202: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7044 - val_loss: 0.0107 - val_acc: 0.6986
Epoch 204/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7038Epoch 00203: val_loss improved from 0.00904 to 0.00868, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7027 - val_loss: 0.0087 - val_acc: 0.6986
Epoch 205/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0040 - acc: 0.7044Epoch 00204: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7056 - val_loss: 0.0101 - val_acc: 0.6963
Epoch 206/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7012Epoch 00205: val_loss improved from 0.00868 to 0.00845, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7033 - val_loss: 0.0085 - val_acc: 0.6986
Epoch 207/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0038 - acc: 0.6960Epoch 00206: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7004 - val_loss: 0.0089 - val_acc: 0.6963
Epoch 208/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7018Epoch 00207: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7039 - val_loss: 0.0109 - val_acc: 0.6963
Epoch 209/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0039 - acc: 0.7064Epoch 00208: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0039 - acc: 0.7056 - val_loss: 0.0089 - val_acc: 0.6963
Epoch 210/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0038 - acc: 0.7057Epoch 00209: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7074 - val_loss: 0.0086 - val_acc: 0.6986
Epoch 211/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0038 - acc: 0.7070Epoch 00210: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7062 - val_loss: 0.0094 - val_acc: 0.6963
Epoch 212/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7025Epoch 00211: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7044 - val_loss: 0.0088 - val_acc: 0.6986
Epoch 213/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7025Epoch 00212: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7044 - val_loss: 0.0093 - val_acc: 0.6963
Epoch 214/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7083Epoch 00213: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7033 - val_loss: 0.0085 - val_acc: 0.6963
Epoch 215/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7083Epoch 00214: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7044 - val_loss: 0.0087 - val_acc: 0.6963
Epoch 216/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7109Epoch 00215: val_loss improved from 0.00845 to 0.00731, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7103 - val_loss: 0.0073 - val_acc: 0.6963
Epoch 217/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7064Epoch 00216: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7056 - val_loss: 0.0094 - val_acc: 0.6963
Epoch 218/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7031Epoch 00217: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7039 - val_loss: 0.0083 - val_acc: 0.6963
Epoch 219/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7025Epoch 00218: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7056 - val_loss: 0.0082 - val_acc: 0.6963
Epoch 220/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7122Epoch 00219: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7091 - val_loss: 0.0092 - val_acc: 0.6963
Epoch 221/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7116Epoch 00220: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0038 - acc: 0.7085 - val_loss: 0.0074 - val_acc: 0.6963
Epoch 222/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7051Epoch 00221: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7044 - val_loss: 0.0100 - val_acc: 0.6963
Epoch 223/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7077Epoch 00222: val_loss improved from 0.00731 to 0.00709, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7074 - val_loss: 0.0071 - val_acc: 0.6963
Epoch 224/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0037 - acc: 0.7083Epoch 00223: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0037 - acc: 0.7085 - val_loss: 0.0091 - val_acc: 0.6963
Epoch 225/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0036 - acc: 0.7083Epoch 00224: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0036 - acc: 0.7062 - val_loss: 0.0076 - val_acc: 0.6963
Epoch 226/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0036 - acc: 0.7051Epoch 00225: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0036 - acc: 0.7056 - val_loss: 0.0079 - val_acc: 0.6963
Epoch 227/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7129Epoch 00226: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0036 - acc: 0.7085 - val_loss: 0.0074 - val_acc: 0.6963
Epoch 228/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0036 - acc: 0.7090Epoch 00227: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0036 - acc: 0.7120 - val_loss: 0.0090 - val_acc: 0.6963
Epoch 229/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7129Epoch 00228: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7103 - val_loss: 0.0076 - val_acc: 0.6963
Epoch 230/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7090Epoch 00229: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7033 - val_loss: 0.0080 - val_acc: 0.6963
Epoch 231/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7012Epoch 00230: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7044 - val_loss: 0.0078 - val_acc: 0.6963
Epoch 232/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7096Epoch 00231: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7068 - val_loss: 0.0074 - val_acc: 0.6963
Epoch 233/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.6999Epoch 00232: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7044 - val_loss: 0.0082 - val_acc: 0.6963
Epoch 234/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7148Epoch 00233: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7103 - val_loss: 0.0072 - val_acc: 0.6963
Epoch 235/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7025Epoch 00234: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7062 - val_loss: 0.0075 - val_acc: 0.6986
Epoch 236/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7064Epoch 00235: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7079 - val_loss: 0.0072 - val_acc: 0.6963
Epoch 237/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7129Epoch 00236: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7120 - val_loss: 0.0085 - val_acc: 0.7033
Epoch 238/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.6999Epoch 00237: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7091 - val_loss: 0.0071 - val_acc: 0.7009
Epoch 239/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7012Epoch 00238: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0035 - acc: 0.7027 - val_loss: 0.0078 - val_acc: 0.6986
Epoch 240/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7044Epoch 00239: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7079 - val_loss: 0.0082 - val_acc: 0.7079
Epoch 241/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7116Epoch 00240: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7062 - val_loss: 0.0078 - val_acc: 0.6986
Epoch 242/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7038Epoch 00241: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7027 - val_loss: 0.0073 - val_acc: 0.6986
Epoch 243/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0035 - acc: 0.7044Epoch 00242: val_loss improved from 0.00709 to 0.00637, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7109 - val_loss: 0.0064 - val_acc: 0.6986
Epoch 244/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7103Epoch 00243: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7097 - val_loss: 0.0080 - val_acc: 0.7033
Epoch 245/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0034 - acc: 0.7057Epoch 00244: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0034 - acc: 0.7050 - val_loss: 0.0081 - val_acc: 0.6986
Epoch 246/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7025Epoch 00245: val_loss improved from 0.00637 to 0.00633, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0033 - acc: 0.7085 - val_loss: 0.0063 - val_acc: 0.7009
Epoch 247/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7051Epoch 00246: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0033 - acc: 0.7097 - val_loss: 0.0076 - val_acc: 0.7009
Epoch 248/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7096Epoch 00247: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0033 - acc: 0.7109 - val_loss: 0.0077 - val_acc: 0.7033
Epoch 249/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7044Epoch 00248: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7015 - val_loss: 0.0073 - val_acc: 0.6986
Epoch 250/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7103Epoch 00249: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7091 - val_loss: 0.0072 - val_acc: 0.6963
Epoch 251/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0032 - acc: 0.7161Epoch 00250: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7109 - val_loss: 0.0077 - val_acc: 0.6986
Epoch 252/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0032 - acc: 0.7129Epoch 00251: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7050 - val_loss: 0.0088 - val_acc: 0.7033
Epoch 253/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0033 - acc: 0.7064Epoch 00252: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0033 - acc: 0.7091 - val_loss: 0.0074 - val_acc: 0.7033
Epoch 254/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7051Epoch 00253: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7056 - val_loss: 0.0065 - val_acc: 0.7009
Epoch 255/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0032 - acc: 0.7116Epoch 00254: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7109 - val_loss: 0.0071 - val_acc: 0.7009
Epoch 256/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0032 - acc: 0.7116Epoch 00255: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7103 - val_loss: 0.0065 - val_acc: 0.7009
Epoch 257/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7122Epoch 00256: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0032 - acc: 0.7103 - val_loss: 0.0065 - val_acc: 0.6986
Epoch 258/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0032 - acc: 0.7077Epoch 00257: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7091 - val_loss: 0.0075 - val_acc: 0.7056
Epoch 259/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7057Epoch 00258: val_loss improved from 0.00633 to 0.00625, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7097 - val_loss: 0.0062 - val_acc: 0.7033
Epoch 260/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7070Epoch 00259: val_loss improved from 0.00625 to 0.00614, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7033 - val_loss: 0.0061 - val_acc: 0.7056
Epoch 261/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7070Epoch 00260: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7050 - val_loss: 0.0070 - val_acc: 0.7079
Epoch 262/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7096Epoch 00261: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7085 - val_loss: 0.0077 - val_acc: 0.7033
Epoch 263/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7083Epoch 00262: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7062 - val_loss: 0.0069 - val_acc: 0.7033
Epoch 264/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.6999Epoch 00263: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7068 - val_loss: 0.0065 - val_acc: 0.7009
Epoch 265/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7227Epoch 00264: val_loss improved from 0.00614 to 0.00605, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0030 - acc: 0.7161 - val_loss: 0.0060 - val_acc: 0.7056
Epoch 266/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7090Epoch 00265: val_loss improved from 0.00605 to 0.00540, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7068 - val_loss: 0.0054 - val_acc: 0.7009
Epoch 267/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7109Epoch 00266: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7126 - val_loss: 0.0066 - val_acc: 0.7079
Epoch 268/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7031Epoch 00267: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0030 - acc: 0.7074 - val_loss: 0.0078 - val_acc: 0.7126
Epoch 269/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0031 - acc: 0.7122Epoch 00268: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0031 - acc: 0.7103 - val_loss: 0.0070 - val_acc: 0.7150
Epoch 270/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7025Epoch 00269: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0030 - acc: 0.7044 - val_loss: 0.0060 - val_acc: 0.7056
Epoch 271/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7142Epoch 00270: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0030 - acc: 0.7097 - val_loss: 0.0064 - val_acc: 0.7173
Epoch 272/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7103Epoch 00271: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7050 - val_loss: 0.0071 - val_acc: 0.7126
Epoch 273/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.7064Epoch 00272: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0030 - acc: 0.7050 - val_loss: 0.0074 - val_acc: 0.7103
Epoch 274/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7057Epoch 00273: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7079 - val_loss: 0.0064 - val_acc: 0.7103
Epoch 275/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0030 - acc: 0.6979Epoch 00274: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7039 - val_loss: 0.0059 - val_acc: 0.7009
Epoch 276/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7103Epoch 00275: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7085 - val_loss: 0.0061 - val_acc: 0.7079
Epoch 277/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7096Epoch 00276: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7109 - val_loss: 0.0074 - val_acc: 0.7056
Epoch 278/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7188Epoch 00277: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7138 - val_loss: 0.0073 - val_acc: 0.7103
Epoch 279/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7122Epoch 00278: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7068 - val_loss: 0.0069 - val_acc: 0.7126
Epoch 280/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7064Epoch 00279: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7056 - val_loss: 0.0059 - val_acc: 0.7103
Epoch 281/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7135Epoch 00280: val_loss improved from 0.00540 to 0.00530, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7144 - val_loss: 0.0053 - val_acc: 0.7150
Epoch 282/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7103Epoch 00281: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7074 - val_loss: 0.0066 - val_acc: 0.7173
Epoch 283/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7148Epoch 00282: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7138 - val_loss: 0.0079 - val_acc: 0.7103
Epoch 284/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7090Epoch 00283: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7109 - val_loss: 0.0058 - val_acc: 0.7079
Epoch 285/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0028 - acc: 0.7077Epoch 00284: val_loss improved from 0.00530 to 0.00490, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7027 - val_loss: 0.0049 - val_acc: 0.7103
Epoch 286/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0029 - acc: 0.7181Epoch 00285: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0029 - acc: 0.7132 - val_loss: 0.0071 - val_acc: 0.7150
Epoch 287/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0028 - acc: 0.7044Epoch 00286: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0028 - acc: 0.7009 - val_loss: 0.0058 - val_acc: 0.7126
Epoch 288/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7194Epoch 00287: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7161 - val_loss: 0.0058 - val_acc: 0.7126
Epoch 289/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7044Epoch 00288: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7079 - val_loss: 0.0058 - val_acc: 0.7173
Epoch 290/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7109Epoch 00289: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7144 - val_loss: 0.0060 - val_acc: 0.7103
Epoch 291/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7188Epoch 00290: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7167 - val_loss: 0.0055 - val_acc: 0.7103
Epoch 292/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7122Epoch 00291: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7103 - val_loss: 0.0057 - val_acc: 0.7126
Epoch 293/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7064Epoch 00292: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7097 - val_loss: 0.0052 - val_acc: 0.7126
Epoch 294/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7161Epoch 00293: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7161 - val_loss: 0.0054 - val_acc: 0.7196
Epoch 295/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7135Epoch 00294: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7085 - val_loss: 0.0055 - val_acc: 0.7103
Epoch 296/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0027 - acc: 0.7142Epoch 00295: val_loss improved from 0.00490 to 0.00483, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0027 - acc: 0.7190 - val_loss: 0.0048 - val_acc: 0.7079
Epoch 297/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7168Epoch 00296: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7179 - val_loss: 0.0053 - val_acc: 0.7103
Epoch 298/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7090Epoch 00297: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7120 - val_loss: 0.0052 - val_acc: 0.7103
Epoch 299/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7044Epoch 00298: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7074 - val_loss: 0.0053 - val_acc: 0.7126
Epoch 300/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7188Epoch 00299: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7138 - val_loss: 0.0052 - val_acc: 0.7150
Epoch 301/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7259Epoch 00300: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7220 - val_loss: 0.0053 - val_acc: 0.7126
Epoch 302/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7135Epoch 00301: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7132 - val_loss: 0.0052 - val_acc: 0.7150
Epoch 303/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7207Epoch 00302: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7173 - val_loss: 0.0052 - val_acc: 0.7243
Epoch 304/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7051Epoch 00303: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0026 - acc: 0.7068 - val_loss: 0.0052 - val_acc: 0.7103
Epoch 305/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0026 - acc: 0.7077Epoch 00304: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7079 - val_loss: 0.0053 - val_acc: 0.7173
Epoch 306/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.6992Epoch 00305: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7079 - val_loss: 0.0053 - val_acc: 0.7150
Epoch 307/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7155Epoch 00306: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7179 - val_loss: 0.0051 - val_acc: 0.7150
Epoch 308/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7155Epoch 00307: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7144 - val_loss: 0.0057 - val_acc: 0.7126
Epoch 309/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7194Epoch 00308: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7161 - val_loss: 0.0057 - val_acc: 0.7173
Epoch 310/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7103Epoch 00309: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7132 - val_loss: 0.0056 - val_acc: 0.7103
Epoch 311/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7116Epoch 00310: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7179 - val_loss: 0.0054 - val_acc: 0.7407
Epoch 312/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7279Epoch 00311: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7261 - val_loss: 0.0055 - val_acc: 0.7243
Epoch 313/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0025 - acc: 0.7194Epoch 00312: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0025 - acc: 0.7196 - val_loss: 0.0049 - val_acc: 0.7126
Epoch 314/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7142Epoch 00313: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7202 - val_loss: 0.0050 - val_acc: 0.7079
Epoch 315/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7305Epoch 00314: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7261 - val_loss: 0.0051 - val_acc: 0.7336
Epoch 316/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7168Epoch 00315: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7120 - val_loss: 0.0050 - val_acc: 0.7126
Epoch 317/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7188Epoch 00316: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0024 - acc: 0.7179 - val_loss: 0.0050 - val_acc: 0.7173
Epoch 318/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7266Epoch 00317: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7185 - val_loss: 0.0052 - val_acc: 0.7220
Epoch 319/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7161Epoch 00318: val_loss improved from 0.00483 to 0.00425, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7179 - val_loss: 0.0043 - val_acc: 0.7079
Epoch 320/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0024 - acc: 0.7279Epoch 00319: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7179 - val_loss: 0.0051 - val_acc: 0.7243
Epoch 321/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7220Epoch 00320: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7237 - val_loss: 0.0053 - val_acc: 0.7150
Epoch 322/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7240Epoch 00321: val_loss improved from 0.00425 to 0.00413, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7301 - val_loss: 0.0041 - val_acc: 0.7126
Epoch 323/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7253Epoch 00322: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7290 - val_loss: 0.0042 - val_acc: 0.7173
Epoch 324/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7266Epoch 00323: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7272 - val_loss: 0.0048 - val_acc: 0.7079
Epoch 325/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7227Epoch 00324: val_loss improved from 0.00413 to 0.00405, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7185 - val_loss: 0.0041 - val_acc: 0.7196
Epoch 326/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7227Epoch 00325: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7243 - val_loss: 0.0041 - val_acc: 0.7103
Epoch 327/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0023 - acc: 0.7318Epoch 00326: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0023 - acc: 0.7243 - val_loss: 0.0046 - val_acc: 0.7103
Epoch 328/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7305Epoch 00327: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7290 - val_loss: 0.0044 - val_acc: 0.7150
Epoch 329/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7305Epoch 00328: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7266 - val_loss: 0.0051 - val_acc: 0.7220
Epoch 330/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7194Epoch 00329: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7214 - val_loss: 0.0053 - val_acc: 0.7313
Epoch 331/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7214Epoch 00330: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7220 - val_loss: 0.0054 - val_acc: 0.7173
Epoch 332/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7207Epoch 00331: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7208 - val_loss: 0.0046 - val_acc: 0.7266
Epoch 333/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7311Epoch 00332: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0022 - acc: 0.7272 - val_loss: 0.0043 - val_acc: 0.7407
Epoch 334/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7311Epoch 00333: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7243 - val_loss: 0.0044 - val_acc: 0.7196
Epoch 335/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7285Epoch 00334: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7278 - val_loss: 0.0048 - val_acc: 0.7290
Epoch 336/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7266Epoch 00335: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7284 - val_loss: 0.0041 - val_acc: 0.7266
Epoch 337/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7311Epoch 00336: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7307 - val_loss: 0.0042 - val_acc: 0.7360
Epoch 338/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7227Epoch 00337: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7278 - val_loss: 0.0050 - val_acc: 0.7407
Epoch 339/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7435Epoch 00338: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7407 - val_loss: 0.0050 - val_acc: 0.7593
Epoch 340/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7305Epoch 00339: val_loss improved from 0.00405 to 0.00395, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7319 - val_loss: 0.0039 - val_acc: 0.7266
Epoch 341/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7318Epoch 00340: val_loss improved from 0.00395 to 0.00383, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7290 - val_loss: 0.0038 - val_acc: 0.7430
Epoch 342/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7337Epoch 00341: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7336 - val_loss: 0.0043 - val_acc: 0.7407
Epoch 343/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7474Epoch 00342: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7447 - val_loss: 0.0045 - val_acc: 0.7593
Epoch 344/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7422Epoch 00343: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7389 - val_loss: 0.0057 - val_acc: 0.7640
Epoch 345/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7318Epoch 00344: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0020 - acc: 0.7342 - val_loss: 0.0057 - val_acc: 0.7407
Epoch 346/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0022 - acc: 0.7292Epoch 00345: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0021 - acc: 0.7325 - val_loss: 0.0058 - val_acc: 0.7407
Epoch 347/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0020 - acc: 0.7337Epoch 00346: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0020 - acc: 0.7325 - val_loss: 0.0045 - val_acc: 0.7593
Epoch 348/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0021 - acc: 0.7383Epoch 00347: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0020 - acc: 0.7401 - val_loss: 0.0040 - val_acc: 0.7477
Epoch 349/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7461Epoch 00348: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7389 - val_loss: 0.0046 - val_acc: 0.7500
Epoch 350/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0020 - acc: 0.7298Epoch 00349: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0020 - acc: 0.7307 - val_loss: 0.0044 - val_acc: 0.7687
Epoch 351/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0020 - acc: 0.7298Epoch 00350: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7377 - val_loss: 0.0043 - val_acc: 0.7547
Epoch 352/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0020 - acc: 0.7298Epoch 00351: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0020 - acc: 0.7348 - val_loss: 0.0044 - val_acc: 0.7477
Epoch 353/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7161Epoch 00352: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7231 - val_loss: 0.0040 - val_acc: 0.7617
Epoch 354/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7363Epoch 00353: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7377 - val_loss: 0.0044 - val_acc: 0.7617
Epoch 355/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7350Epoch 00354: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7348 - val_loss: 0.0048 - val_acc: 0.7407
Epoch 356/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7396Epoch 00355: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7407 - val_loss: 0.0046 - val_acc: 0.7407
Epoch 357/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7357Epoch 00356: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7395 - val_loss: 0.0042 - val_acc: 0.7547
Epoch 358/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7344Epoch 00357: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7389 - val_loss: 0.0045 - val_acc: 0.7593
Epoch 359/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7415Epoch 00358: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7412 - val_loss: 0.0042 - val_acc: 0.7710
Epoch 360/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7357Epoch 00359: val_loss improved from 0.00383 to 0.00383, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7377 - val_loss: 0.0038 - val_acc: 0.7523
Epoch 361/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7461Epoch 00360: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7512 - val_loss: 0.0039 - val_acc: 0.7523
Epoch 362/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7513Epoch 00361: val_loss improved from 0.00383 to 0.00369, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0019 - acc: 0.7500 - val_loss: 0.0037 - val_acc: 0.7710
Epoch 363/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7435Epoch 00362: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7465 - val_loss: 0.0040 - val_acc: 0.7640
Epoch 364/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7376Epoch 00363: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7395 - val_loss: 0.0038 - val_acc: 0.7336
Epoch 365/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7422Epoch 00364: val_loss improved from 0.00369 to 0.00358, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7430 - val_loss: 0.0036 - val_acc: 0.7617
Epoch 366/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0019 - acc: 0.7396Epoch 00365: val_loss improved from 0.00358 to 0.00311, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7447 - val_loss: 0.0031 - val_acc: 0.7593
Epoch 367/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7441Epoch 00366: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7471 - val_loss: 0.0034 - val_acc: 0.7453
Epoch 368/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7428Epoch 00367: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7412 - val_loss: 0.0035 - val_acc: 0.7710
Epoch 369/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7357Epoch 00368: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7407 - val_loss: 0.0039 - val_acc: 0.7710
Epoch 370/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7441Epoch 00369: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7459 - val_loss: 0.0040 - val_acc: 0.7664
Epoch 371/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7441Epoch 00370: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7430 - val_loss: 0.0036 - val_acc: 0.7523
Epoch 372/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7513Epoch 00371: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7523 - val_loss: 0.0036 - val_acc: 0.7734
Epoch 373/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7376Epoch 00372: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7407 - val_loss: 0.0040 - val_acc: 0.7734
Epoch 374/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7520Epoch 00373: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7506 - val_loss: 0.0038 - val_acc: 0.7500
Epoch 375/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7389Epoch 00374: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7447 - val_loss: 0.0039 - val_acc: 0.7336
Epoch 376/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7565Epoch 00375: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7617 - val_loss: 0.0037 - val_acc: 0.7313
Epoch 377/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7507Epoch 00376: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7547 - val_loss: 0.0037 - val_acc: 0.7664
Epoch 378/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7415Epoch 00377: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7436 - val_loss: 0.0039 - val_acc: 0.7734
Epoch 379/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7487Epoch 00378: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7518 - val_loss: 0.0039 - val_acc: 0.7827
Epoch 380/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7604Epoch 00379: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7623 - val_loss: 0.0048 - val_acc: 0.7874
Epoch 381/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7572Epoch 00380: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7593 - val_loss: 0.0047 - val_acc: 0.7991
Epoch 382/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0018 - acc: 0.7409Epoch 00381: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0018 - acc: 0.7447 - val_loss: 0.0042 - val_acc: 0.7734
Epoch 383/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7409Epoch 00382: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7424 - val_loss: 0.0040 - val_acc: 0.7757
Epoch 384/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7572Epoch 00383: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7570 - val_loss: 0.0040 - val_acc: 0.7804
Epoch 385/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7565Epoch 00384: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7576 - val_loss: 0.0041 - val_acc: 0.7593
Epoch 386/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0017 - acc: 0.7572Epoch 00385: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7582 - val_loss: 0.0039 - val_acc: 0.7804
Epoch 387/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7650Epoch 00386: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7593 - val_loss: 0.0033 - val_acc: 0.7804
Epoch 388/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7598Epoch 00387: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7588 - val_loss: 0.0032 - val_acc: 0.7640
Epoch 389/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7591Epoch 00388: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0017 - acc: 0.7629 - val_loss: 0.0034 - val_acc: 0.7640
Epoch 390/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7546Epoch 00389: val_loss improved from 0.00311 to 0.00311, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7582 - val_loss: 0.0031 - val_acc: 0.7664
Epoch 391/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7650Epoch 00390: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7547 - val_loss: 0.0036 - val_acc: 0.7944
Epoch 392/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7741Epoch 00391: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7728 - val_loss: 0.0034 - val_acc: 0.7757
Epoch 393/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7520Epoch 00392: val_loss improved from 0.00311 to 0.00279, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7605 - val_loss: 0.0028 - val_acc: 0.7874
Epoch 394/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7552Epoch 00393: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7558 - val_loss: 0.0029 - val_acc: 0.7850
Epoch 395/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7507Epoch 00394: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7482 - val_loss: 0.0031 - val_acc: 0.7874
Epoch 396/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7565Epoch 00395: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7558 - val_loss: 0.0037 - val_acc: 0.7710
Epoch 397/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7533Epoch 00396: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7535 - val_loss: 0.0038 - val_acc: 0.7640
Epoch 398/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7585Epoch 00397: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0016 - acc: 0.7605 - val_loss: 0.0030 - val_acc: 0.7664
Epoch 399/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7643Epoch 00398: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7693 - val_loss: 0.0032 - val_acc: 0.7804
Epoch 400/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7682Epoch 00399: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7652 - val_loss: 0.0033 - val_acc: 0.7850
Epoch 401/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7715Epoch 00400: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7681 - val_loss: 0.0043 - val_acc: 0.7734
Epoch 402/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7637Epoch 00401: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7646 - val_loss: 0.0040 - val_acc: 0.7780
Epoch 403/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7598Epoch 00402: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7588 - val_loss: 0.0035 - val_acc: 0.7757
Epoch 404/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7650Epoch 00403: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7669 - val_loss: 0.0033 - val_acc: 0.7804
Epoch 405/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7617Epoch 00404: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7629 - val_loss: 0.0032 - val_acc: 0.7757
Epoch 406/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7637Epoch 00405: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7669 - val_loss: 0.0029 - val_acc: 0.7780
Epoch 407/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7650Epoch 00406: val_loss improved from 0.00279 to 0.00262, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7652 - val_loss: 0.0026 - val_acc: 0.7827
Epoch 408/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7604Epoch 00407: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7541 - val_loss: 0.0030 - val_acc: 0.7921
Epoch 409/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7669Epoch 00408: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7681 - val_loss: 0.0030 - val_acc: 0.7897
Epoch 410/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7493Epoch 00409: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7588 - val_loss: 0.0031 - val_acc: 0.7827
Epoch 411/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7819Epoch 00410: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7804 - val_loss: 0.0038 - val_acc: 0.7897
Epoch 412/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0016 - acc: 0.7539Epoch 00411: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7629 - val_loss: 0.0038 - val_acc: 0.7757
Epoch 413/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7630Epoch 00412: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7669 - val_loss: 0.0042 - val_acc: 0.7944
Epoch 414/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7643Epoch 00413: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7629 - val_loss: 0.0032 - val_acc: 0.7967
Epoch 415/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7663Epoch 00414: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7699 - val_loss: 0.0035 - val_acc: 0.7827
Epoch 416/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7760Epoch 00415: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7699 - val_loss: 0.0029 - val_acc: 0.7874
Epoch 417/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7643Epoch 00416: val_loss improved from 0.00262 to 0.00246, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7652 - val_loss: 0.0025 - val_acc: 0.7827
Epoch 418/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7643Epoch 00417: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0015 - acc: 0.7640 - val_loss: 0.0027 - val_acc: 0.7874
Epoch 419/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0015 - acc: 0.7806Epoch 00418: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7786 - val_loss: 0.0031 - val_acc: 0.7921
Epoch 420/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7878Epoch 00419: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7786 - val_loss: 0.0031 - val_acc: 0.7850
Epoch 421/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7624Epoch 00420: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7652 - val_loss: 0.0034 - val_acc: 0.8014
Epoch 422/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7734Epoch 00421: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7716 - val_loss: 0.0035 - val_acc: 0.7897
Epoch 423/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7773Epoch 00422: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7699 - val_loss: 0.0032 - val_acc: 0.7593
Epoch 424/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7695Epoch 00423: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7658 - val_loss: 0.0036 - val_acc: 0.7921
Epoch 425/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7773Epoch 00424: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7745 - val_loss: 0.0034 - val_acc: 0.8084
Epoch 426/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7773Epoch 00425: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7751 - val_loss: 0.0028 - val_acc: 0.7850
Epoch 427/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7845Epoch 00426: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7850 - val_loss: 0.0030 - val_acc: 0.8037
Epoch 428/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7695Epoch 00427: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7745 - val_loss: 0.0031 - val_acc: 0.7921
Epoch 429/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7617Epoch 00428: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7669 - val_loss: 0.0032 - val_acc: 0.7850
Epoch 430/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7839Epoch 00429: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7792 - val_loss: 0.0029 - val_acc: 0.7967
Epoch 431/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7721Epoch 00430: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7704 - val_loss: 0.0029 - val_acc: 0.7850
Epoch 432/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7741Epoch 00431: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7769 - val_loss: 0.0030 - val_acc: 0.7897
Epoch 433/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7819Epoch 00432: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7775 - val_loss: 0.0033 - val_acc: 0.7850
Epoch 434/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7812Epoch 00433: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7850 - val_loss: 0.0032 - val_acc: 0.7991
Epoch 435/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7832Epoch 00434: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7845 - val_loss: 0.0027 - val_acc: 0.7897
Epoch 436/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7773Epoch 00435: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7734 - val_loss: 0.0036 - val_acc: 0.8037
Epoch 437/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0014 - acc: 0.7865Epoch 00436: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0014 - acc: 0.7856 - val_loss: 0.0035 - val_acc: 0.7827
Epoch 438/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7786Epoch 00437: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7792 - val_loss: 0.0031 - val_acc: 0.7921
Epoch 439/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7786Epoch 00438: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7757 - val_loss: 0.0032 - val_acc: 0.7897
Epoch 440/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7695Epoch 00439: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7716 - val_loss: 0.0037 - val_acc: 0.8107
Epoch 441/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7598Epoch 00440: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7634 - val_loss: 0.0034 - val_acc: 0.8084
Epoch 442/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7852Epoch 00441: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7810 - val_loss: 0.0032 - val_acc: 0.8037
Epoch 443/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7734Epoch 00442: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7798 - val_loss: 0.0030 - val_acc: 0.8084
Epoch 444/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7773Epoch 00443: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7745 - val_loss: 0.0030 - val_acc: 0.8154
Epoch 445/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7812Epoch 00444: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7792 - val_loss: 0.0033 - val_acc: 0.7991
Epoch 446/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7799Epoch 00445: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7833 - val_loss: 0.0029 - val_acc: 0.8084
Epoch 447/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7708Epoch 00446: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7710 - val_loss: 0.0026 - val_acc: 0.7850
Epoch 448/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7786Epoch 00447: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7792 - val_loss: 0.0027 - val_acc: 0.8131
Epoch 449/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7819Epoch 00448: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7850 - val_loss: 0.0028 - val_acc: 0.8014
Epoch 450/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7878Epoch 00449: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7909 - val_loss: 0.0033 - val_acc: 0.8131
Epoch 451/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7852Epoch 00450: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7886 - val_loss: 0.0031 - val_acc: 0.7921
Epoch 452/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.8001Epoch 00451: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7950 - val_loss: 0.0028 - val_acc: 0.7897
Epoch 453/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7845Epoch 00452: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7833 - val_loss: 0.0029 - val_acc: 0.7991
Epoch 454/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7845Epoch 00453: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7856 - val_loss: 0.0030 - val_acc: 0.7944
Epoch 455/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7832Epoch 00454: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7856 - val_loss: 0.0028 - val_acc: 0.7967
Epoch 456/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7897Epoch 00455: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7874 - val_loss: 0.0026 - val_acc: 0.7921
Epoch 457/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7917Epoch 00456: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7886 - val_loss: 0.0038 - val_acc: 0.8178
Epoch 458/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7878Epoch 00457: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7827 - val_loss: 0.0038 - val_acc: 0.8037
Epoch 459/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7891Epoch 00458: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7868 - val_loss: 0.0038 - val_acc: 0.8107
Epoch 460/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7917Epoch 00459: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7915 - val_loss: 0.0036 - val_acc: 0.8154
Epoch 461/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0013 - acc: 0.7754Epoch 00460: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0013 - acc: 0.7775 - val_loss: 0.0029 - val_acc: 0.7967
Epoch 462/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7812Epoch 00461: val_loss improved from 0.00246 to 0.00233, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7821 - val_loss: 0.0023 - val_acc: 0.8061
Epoch 463/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7910Epoch 00462: val_loss improved from 0.00233 to 0.00229, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7944 - val_loss: 0.0023 - val_acc: 0.8014
Epoch 464/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.8001Epoch 00463: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7961 - val_loss: 0.0024 - val_acc: 0.8224
Epoch 465/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7936Epoch 00464: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7932 - val_loss: 0.0026 - val_acc: 0.8178
Epoch 466/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7910Epoch 00465: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7915 - val_loss: 0.0023 - val_acc: 0.7897
Epoch 467/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.8014Epoch 00466: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.8008 - val_loss: 0.0024 - val_acc: 0.8178
Epoch 468/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7975Epoch 00467: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7944 - val_loss: 0.0027 - val_acc: 0.7991
Epoch 469/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7936Epoch 00468: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7932 - val_loss: 0.0029 - val_acc: 0.7944
Epoch 470/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7858Epoch 00469: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7909 - val_loss: 0.0030 - val_acc: 0.8061
Epoch 471/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7793Epoch 00470: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7792 - val_loss: 0.0032 - val_acc: 0.8154
Epoch 472/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0012 - acc: 0.7917Epoch 00471: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0012 - acc: 0.7868 - val_loss: 0.0031 - val_acc: 0.7850
Epoch 473/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7962Epoch 00472: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7926 - val_loss: 0.0028 - val_acc: 0.8061
Epoch 474/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7956Epoch 00473: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7985 - val_loss: 0.0027 - val_acc: 0.8178
Epoch 475/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7975Epoch 00474: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7973 - val_loss: 0.0030 - val_acc: 0.8061
Epoch 476/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7962Epoch 00475: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7944 - val_loss: 0.0025 - val_acc: 0.8061
Epoch 477/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7969Epoch 00476: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7944 - val_loss: 0.0029 - val_acc: 0.7967
Epoch 478/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7917Epoch 00477: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7915 - val_loss: 0.0026 - val_acc: 0.8107
Epoch 479/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.8001Epoch 00478: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7996 - val_loss: 0.0025 - val_acc: 0.8014
Epoch 480/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7982Epoch 00479: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7985 - val_loss: 0.0025 - val_acc: 0.8084
Epoch 481/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7956Epoch 00480: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7950 - val_loss: 0.0027 - val_acc: 0.8131
Epoch 482/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7917Epoch 00481: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7973 - val_loss: 0.0031 - val_acc: 0.8107
Epoch 483/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.8079Epoch 00482: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.8049 - val_loss: 0.0030 - val_acc: 0.8178
Epoch 484/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7969Epoch 00483: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7921 - val_loss: 0.0034 - val_acc: 0.8107
Epoch 485/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7936Epoch 00484: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7932 - val_loss: 0.0033 - val_acc: 0.8154
Epoch 486/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7910Epoch 00485: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7938 - val_loss: 0.0030 - val_acc: 0.7967
Epoch 487/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7936Epoch 00486: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7961 - val_loss: 0.0028 - val_acc: 0.8201
Epoch 488/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7891Epoch 00487: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7903 - val_loss: 0.0024 - val_acc: 0.7991
Epoch 489/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.8073Epoch 00488: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.8032 - val_loss: 0.0024 - val_acc: 0.8061
Epoch 490/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.7956Epoch 00489: val_loss improved from 0.00229 to 0.00203, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7991 - val_loss: 0.0020 - val_acc: 0.8037
Epoch 491/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.7910Epoch 00490: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.7891 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 492/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.8053Epoch 00491: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.8043 - val_loss: 0.0024 - val_acc: 0.8107
Epoch 493/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8060   Epoch 00492: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8072 - val_loss: 0.0028 - val_acc: 0.8107
Epoch 494/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.7956Epoch 00493: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.7979 - val_loss: 0.0029 - val_acc: 0.8014
Epoch 495/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0011 - acc: 0.8145Epoch 00494: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0011 - acc: 0.8119 - val_loss: 0.0025 - val_acc: 0.8084
Epoch 496/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.7930Epoch 00495: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.7967 - val_loss: 0.0025 - val_acc: 0.8131
Epoch 497/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.9323e-04 - acc: 0.7995Epoch 00496: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.7991 - val_loss: 0.0025 - val_acc: 0.7804
Epoch 498/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8073Epoch 00497: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8072 - val_loss: 0.0023 - val_acc: 0.8107
Epoch 499/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8092Epoch 00498: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8067 - val_loss: 0.0023 - val_acc: 0.7827
Epoch 500/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.7962Epoch 00499: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.7973 - val_loss: 0.0024 - val_acc: 0.8131
Epoch 501/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8099 Epoch 00500: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8043 - val_loss: 0.0026 - val_acc: 0.7991
Epoch 502/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8021Epoch 00501: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8020 - val_loss: 0.0026 - val_acc: 0.8084
Epoch 503/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.8066    Epoch 00502: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.8043 - val_loss: 0.0024 - val_acc: 0.8084
Epoch 504/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8868e-04 - acc: 0.8112Epoch 00503: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8956e-04 - acc: 0.8102 - val_loss: 0.0023 - val_acc: 0.8084
Epoch 505/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8958e-04 - acc: 0.8118Epoch 00504: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8189e-04 - acc: 0.8084 - val_loss: 0.0025 - val_acc: 0.8014
Epoch 506/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.9126e-04 - acc: 0.7910Epoch 00505: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8123e-04 - acc: 0.7938 - val_loss: 0.0025 - val_acc: 0.8107
Epoch 507/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.7590e-04 - acc: 0.8060Epoch 00506: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8233e-04 - acc: 0.8043 - val_loss: 0.0025 - val_acc: 0.8131
Epoch 508/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8995e-04 - acc: 0.8060Epoch 00507: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.7720e-04 - acc: 0.8084 - val_loss: 0.0025 - val_acc: 0.8037
Epoch 509/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.6436e-04 - acc: 0.8092Epoch 00508: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.7750e-04 - acc: 0.8107 - val_loss: 0.0025 - val_acc: 0.8014
Epoch 510/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8968e-04 - acc: 0.8008Epoch 00509: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8345e-04 - acc: 0.7991 - val_loss: 0.0023 - val_acc: 0.8178
Epoch 511/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.7452e-04 - acc: 0.8053Epoch 00510: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.7812e-04 - acc: 0.8032 - val_loss: 0.0030 - val_acc: 0.8037
Epoch 512/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 0.0010 - acc: 0.7962Epoch 00511: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 0.0010 - acc: 0.7996 - val_loss: 0.0023 - val_acc: 0.8037
Epoch 513/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.3771e-04 - acc: 0.8047Epoch 00512: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.4935e-04 - acc: 0.8008 - val_loss: 0.0022 - val_acc: 0.8131
Epoch 514/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.5655e-04 - acc: 0.7923Epoch 00513: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.5000e-04 - acc: 0.7921 - val_loss: 0.0024 - val_acc: 0.8131
Epoch 515/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.5171e-04 - acc: 0.8060Epoch 00514: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.4443e-04 - acc: 0.8055 - val_loss: 0.0024 - val_acc: 0.8154
Epoch 516/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.4036e-04 - acc: 0.8164Epoch 00515: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.3546e-04 - acc: 0.8178 - val_loss: 0.0027 - val_acc: 0.8037
Epoch 517/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.3530e-04 - acc: 0.8132Epoch 00516: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.3540e-04 - acc: 0.8107 - val_loss: 0.0021 - val_acc: 0.8014
Epoch 518/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.5712e-04 - acc: 0.8105Epoch 00517: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.4972e-04 - acc: 0.8061 - val_loss: 0.0027 - val_acc: 0.8037
Epoch 519/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.5780e-04 - acc: 0.7956Epoch 00518: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.5259e-04 - acc: 0.7944 - val_loss: 0.0022 - val_acc: 0.7991
Epoch 520/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.4722e-04 - acc: 0.8125Epoch 00519: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.4891e-04 - acc: 0.8119 - val_loss: 0.0030 - val_acc: 0.8061
Epoch 521/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8581e-04 - acc: 0.7982Epoch 00520: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.9701e-04 - acc: 0.8008 - val_loss: 0.0026 - val_acc: 0.8107
Epoch 522/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.9224e-04 - acc: 0.8164Epoch 00521: val_loss improved from 0.00203 to 0.00195, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 9.9804e-04 - acc: 0.8183 - val_loss: 0.0020 - val_acc: 0.8131
Epoch 523/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.6309e-04 - acc: 0.7988Epoch 00522: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.6445e-04 - acc: 0.8026 - val_loss: 0.0021 - val_acc: 0.8084
Epoch 524/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.1870e-04 - acc: 0.8053Epoch 00523: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.2233e-04 - acc: 0.8102 - val_loss: 0.0021 - val_acc: 0.8201
Epoch 525/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.2725e-04 - acc: 0.8105Epoch 00524: val_loss improved from 0.00195 to 0.00175, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 9.3068e-04 - acc: 0.8090 - val_loss: 0.0017 - val_acc: 0.8084
Epoch 526/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.8429e-04 - acc: 0.8171Epoch 00525: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.8302e-04 - acc: 0.8183 - val_loss: 0.0020 - val_acc: 0.8107
Epoch 527/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.3422e-04 - acc: 0.8099Epoch 00526: val_loss improved from 0.00175 to 0.00173, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 9.3724e-04 - acc: 0.8113 - val_loss: 0.0017 - val_acc: 0.8037
Epoch 528/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.6225e-04 - acc: 0.8092Epoch 00527: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.5379e-04 - acc: 0.8090 - val_loss: 0.0019 - val_acc: 0.8084
Epoch 529/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.1094e-04 - acc: 0.8053Epoch 00528: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.2070e-04 - acc: 0.8067 - val_loss: 0.0020 - val_acc: 0.8131
Epoch 530/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.2258e-04 - acc: 0.8151Epoch 00529: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.3622e-04 - acc: 0.8084 - val_loss: 0.0023 - val_acc: 0.8037
Epoch 531/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.2071e-04 - acc: 0.8079Epoch 00530: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.1184e-04 - acc: 0.8107 - val_loss: 0.0025 - val_acc: 0.8131
Epoch 532/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.1489e-04 - acc: 0.8281Epoch 00531: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.1450e-04 - acc: 0.8306 - val_loss: 0.0024 - val_acc: 0.8084
Epoch 533/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.0020e-04 - acc: 0.8027Epoch 00532: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.0255e-04 - acc: 0.8049 - val_loss: 0.0025 - val_acc: 0.7921
Epoch 534/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.0680e-04 - acc: 0.8203Epoch 00533: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.0747e-04 - acc: 0.8178 - val_loss: 0.0025 - val_acc: 0.7897
Epoch 535/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.8512e-04 - acc: 0.8210Epoch 00534: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.8001e-04 - acc: 0.8213 - val_loss: 0.0022 - val_acc: 0.8037
Epoch 536/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.6651e-04 - acc: 0.8158Epoch 00535: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.6715e-04 - acc: 0.8166 - val_loss: 0.0022 - val_acc: 0.7967
Epoch 537/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.9385e-04 - acc: 0.8203Epoch 00536: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.8268e-04 - acc: 0.8195 - val_loss: 0.0024 - val_acc: 0.8224
Epoch 538/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.8182e-04 - acc: 0.8242Epoch 00537: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.7792e-04 - acc: 0.8248 - val_loss: 0.0025 - val_acc: 0.8061
Epoch 539/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.6306e-04 - acc: 0.8275Epoch 00538: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.6387e-04 - acc: 0.8230 - val_loss: 0.0026 - val_acc: 0.8131
Epoch 540/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5462e-04 - acc: 0.8105Epoch 00539: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5762e-04 - acc: 0.8125 - val_loss: 0.0024 - val_acc: 0.8107
Epoch 541/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.4818e-04 - acc: 0.8118Epoch 00540: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5463e-04 - acc: 0.8119 - val_loss: 0.0027 - val_acc: 0.7967
Epoch 542/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.7773e-04 - acc: 0.8040Epoch 00541: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.7243e-04 - acc: 0.8067 - val_loss: 0.0025 - val_acc: 0.8084
Epoch 543/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5703e-04 - acc: 0.8099Epoch 00542: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.4939e-04 - acc: 0.8166 - val_loss: 0.0022 - val_acc: 0.8014
Epoch 544/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5699e-04 - acc: 0.8034Epoch 00543: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.4714e-04 - acc: 0.8078 - val_loss: 0.0019 - val_acc: 0.8224
Epoch 545/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5316e-04 - acc: 0.8340Epoch 00544: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5126e-04 - acc: 0.8347 - val_loss: 0.0020 - val_acc: 0.8154
Epoch 546/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.3430e-04 - acc: 0.8236Epoch 00545: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.3606e-04 - acc: 0.8259 - val_loss: 0.0021 - val_acc: 0.8178
Epoch 547/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.4273e-04 - acc: 0.8236Epoch 00546: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.4946e-04 - acc: 0.8218 - val_loss: 0.0028 - val_acc: 0.8154
Epoch 548/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.9297e-04 - acc: 0.8275Epoch 00547: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.8661e-04 - acc: 0.8265 - val_loss: 0.0023 - val_acc: 0.8037
Epoch 549/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5254e-04 - acc: 0.8138Epoch 00548: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5409e-04 - acc: 0.8113 - val_loss: 0.0020 - val_acc: 0.8154
Epoch 550/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.7606e-04 - acc: 0.8158Epoch 00549: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.6780e-04 - acc: 0.8213 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 551/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5223e-04 - acc: 0.8171Epoch 00550: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5846e-04 - acc: 0.8178 - val_loss: 0.0024 - val_acc: 0.8084
Epoch 552/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5243e-04 - acc: 0.8281Epoch 00551: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5821e-04 - acc: 0.8271 - val_loss: 0.0027 - val_acc: 0.8107
Epoch 553/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.8831e-04 - acc: 0.8236Epoch 00552: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.7653e-04 - acc: 0.8195 - val_loss: 0.0028 - val_acc: 0.8154
Epoch 554/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5415e-04 - acc: 0.8210Epoch 00553: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.5403e-04 - acc: 0.8201 - val_loss: 0.0027 - val_acc: 0.8154
Epoch 555/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.5090e-04 - acc: 0.8099Epoch 00554: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.3992e-04 - acc: 0.8178 - val_loss: 0.0027 - val_acc: 0.8271
Epoch 556/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 9.0484e-04 - acc: 0.8197Epoch 00555: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 9.0097e-04 - acc: 0.8195 - val_loss: 0.0030 - val_acc: 0.8271
Epoch 557/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.7752e-04 - acc: 0.8223Epoch 00556: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.8428e-04 - acc: 0.8230 - val_loss: 0.0025 - val_acc: 0.8084
Epoch 558/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.3999e-04 - acc: 0.8171Epoch 00557: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.4067e-04 - acc: 0.8195 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 559/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.3428e-04 - acc: 0.8171Epoch 00558: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.2935e-04 - acc: 0.8160 - val_loss: 0.0018 - val_acc: 0.8178
Epoch 560/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.2699e-04 - acc: 0.8177Epoch 00559: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.1490e-04 - acc: 0.8207 - val_loss: 0.0021 - val_acc: 0.8131
Epoch 561/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.1697e-04 - acc: 0.8242Epoch 00560: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.1252e-04 - acc: 0.8254 - val_loss: 0.0021 - val_acc: 0.8154
Epoch 562/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.9101e-04 - acc: 0.8288Epoch 00561: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.9762e-04 - acc: 0.8236 - val_loss: 0.0025 - val_acc: 0.8201
Epoch 563/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.0958e-04 - acc: 0.8359Epoch 00562: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.0852e-04 - acc: 0.8294 - val_loss: 0.0023 - val_acc: 0.8131
Epoch 564/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 8.0246e-04 - acc: 0.8216Epoch 00563: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 8.0165e-04 - acc: 0.8189 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 565/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.8157e-04 - acc: 0.8275Epoch 00564: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.8837e-04 - acc: 0.8218 - val_loss: 0.0021 - val_acc: 0.8178
Epoch 566/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.9298e-04 - acc: 0.8164Epoch 00565: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.8717e-04 - acc: 0.8178 - val_loss: 0.0023 - val_acc: 0.8154
Epoch 567/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.9503e-04 - acc: 0.8301Epoch 00566: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.9811e-04 - acc: 0.8283 - val_loss: 0.0022 - val_acc: 0.8248
Epoch 568/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7765e-04 - acc: 0.8151Epoch 00567: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.8501e-04 - acc: 0.8125 - val_loss: 0.0022 - val_acc: 0.8248
Epoch 569/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.8541e-04 - acc: 0.8216Epoch 00568: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.8131e-04 - acc: 0.8271 - val_loss: 0.0024 - val_acc: 0.8131
Epoch 570/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7999e-04 - acc: 0.8229Epoch 00569: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.8264e-04 - acc: 0.8224 - val_loss: 0.0023 - val_acc: 0.8318
Epoch 571/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7409e-04 - acc: 0.8268Epoch 00570: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.7395e-04 - acc: 0.8254 - val_loss: 0.0020 - val_acc: 0.8224
Epoch 572/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5270e-04 - acc: 0.8249Epoch 00571: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5924e-04 - acc: 0.8289 - val_loss: 0.0019 - val_acc: 0.8178
Epoch 573/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.6114e-04 - acc: 0.8164Epoch 00572: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6008e-04 - acc: 0.8183 - val_loss: 0.0021 - val_acc: 0.8201
Epoch 574/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.6167e-04 - acc: 0.8294Epoch 00573: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5668e-04 - acc: 0.8347 - val_loss: 0.0022 - val_acc: 0.8248
Epoch 575/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7383e-04 - acc: 0.8138Epoch 00574: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6927e-04 - acc: 0.8166 - val_loss: 0.0022 - val_acc: 0.8037
Epoch 576/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5899e-04 - acc: 0.8236Epoch 00575: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6516e-04 - acc: 0.8230 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 577/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5989e-04 - acc: 0.8451Epoch 00576: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5984e-04 - acc: 0.8435 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 578/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7463e-04 - acc: 0.8171Epoch 00577: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6905e-04 - acc: 0.8207 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 579/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.6936e-04 - acc: 0.8210Epoch 00578: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6999e-04 - acc: 0.8242 - val_loss: 0.0021 - val_acc: 0.8154
Epoch 580/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5439e-04 - acc: 0.8281Epoch 00579: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5295e-04 - acc: 0.8277 - val_loss: 0.0022 - val_acc: 0.8107
Epoch 581/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.3051e-04 - acc: 0.8255Epoch 00580: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.3479e-04 - acc: 0.8248 - val_loss: 0.0021 - val_acc: 0.8154
Epoch 582/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.3880e-04 - acc: 0.8132Epoch 00581: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.4580e-04 - acc: 0.8131 - val_loss: 0.0021 - val_acc: 0.8131
Epoch 583/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.4385e-04 - acc: 0.8327Epoch 00582: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.4081e-04 - acc: 0.8312 - val_loss: 0.0021 - val_acc: 0.8248
Epoch 584/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5943e-04 - acc: 0.8236Epoch 00583: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6804e-04 - acc: 0.8248 - val_loss: 0.0024 - val_acc: 0.8154
Epoch 585/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.4912e-04 - acc: 0.8171Epoch 00584: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5283e-04 - acc: 0.8195 - val_loss: 0.0022 - val_acc: 0.8107
Epoch 586/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5117e-04 - acc: 0.8242Epoch 00585: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5028e-04 - acc: 0.8254 - val_loss: 0.0021 - val_acc: 0.8201
Epoch 587/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2422e-04 - acc: 0.8398Epoch 00586: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.2369e-04 - acc: 0.8341 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 588/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2992e-04 - acc: 0.8340Epoch 00587: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.3661e-04 - acc: 0.8277 - val_loss: 0.0024 - val_acc: 0.8248
Epoch 589/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.3089e-04 - acc: 0.8210Epoch 00588: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.3272e-04 - acc: 0.8259 - val_loss: 0.0025 - val_acc: 0.8037
Epoch 590/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.5394e-04 - acc: 0.8190Epoch 00589: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5070e-04 - acc: 0.8213 - val_loss: 0.0022 - val_acc: 0.7967
Epoch 591/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.4652e-04 - acc: 0.8281Epoch 00590: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.5756e-04 - acc: 0.8294 - val_loss: 0.0018 - val_acc: 0.8178
Epoch 592/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.7345e-04 - acc: 0.8288Epoch 00591: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6717e-04 - acc: 0.8300 - val_loss: 0.0019 - val_acc: 0.8201
Epoch 593/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2313e-04 - acc: 0.8333Epoch 00592: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.1733e-04 - acc: 0.8370 - val_loss: 0.0020 - val_acc: 0.8154
Epoch 594/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.3787e-04 - acc: 0.8372Epoch 00593: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.4287e-04 - acc: 0.8359 - val_loss: 0.0025 - val_acc: 0.8201
Epoch 595/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.4601e-04 - acc: 0.8301Epoch 00594: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.3946e-04 - acc: 0.8289 - val_loss: 0.0024 - val_acc: 0.8178
Epoch 596/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.3107e-04 - acc: 0.8086Epoch 00595: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.3072e-04 - acc: 0.8137 - val_loss: 0.0020 - val_acc: 0.8154
Epoch 597/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2241e-04 - acc: 0.8171Epoch 00596: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.1462e-04 - acc: 0.8218 - val_loss: 0.0021 - val_acc: 0.8201
Epoch 598/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0231e-04 - acc: 0.8294Epoch 00597: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.0038e-04 - acc: 0.8265 - val_loss: 0.0019 - val_acc: 0.8154
Epoch 599/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0207e-04 - acc: 0.8190Epoch 00598: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.0255e-04 - acc: 0.8224 - val_loss: 0.0018 - val_acc: 0.8201
Epoch 600/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.1815e-04 - acc: 0.8314Epoch 00599: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.2641e-04 - acc: 0.8382 - val_loss: 0.0021 - val_acc: 0.8154
Epoch 601/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.9837e-04 - acc: 0.8190Epoch 00600: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.9851e-04 - acc: 0.8213 - val_loss: 0.0022 - val_acc: 0.8154
Epoch 602/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.8473e-04 - acc: 0.8438Epoch 00601: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.8711e-04 - acc: 0.8446 - val_loss: 0.0021 - val_acc: 0.8271
Epoch 603/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0032e-04 - acc: 0.8418Epoch 00602: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.0191e-04 - acc: 0.8405 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 604/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0233e-04 - acc: 0.8294Epoch 00603: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.9979e-04 - acc: 0.8289 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 605/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.8472e-04 - acc: 0.8385Epoch 00604: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.9098e-04 - acc: 0.8329 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 606/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.9132e-04 - acc: 0.8223Epoch 00605: val_loss improved from 0.00173 to 0.00169, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 6.9016e-04 - acc: 0.8271 - val_loss: 0.0017 - val_acc: 0.8294
Epoch 607/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.6130e-04 - acc: 0.8379Epoch 00606: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.6250e-04 - acc: 0.8265 - val_loss: 0.0021 - val_acc: 0.8131
Epoch 608/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.9808e-04 - acc: 0.8333Epoch 00607: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.9885e-04 - acc: 0.8359 - val_loss: 0.0025 - val_acc: 0.8178
Epoch 609/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2079e-04 - acc: 0.8451Epoch 00608: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.2263e-04 - acc: 0.8400 - val_loss: 0.0025 - val_acc: 0.8294
Epoch 610/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.2581e-04 - acc: 0.8398Epoch 00609: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.2443e-04 - acc: 0.8382 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 611/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.9942e-04 - acc: 0.8353Epoch 00610: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 7.0204e-04 - acc: 0.8341 - val_loss: 0.0018 - val_acc: 0.8201
Epoch 612/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7520e-04 - acc: 0.8333Epoch 00611: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7700e-04 - acc: 0.8376 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 613/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7214e-04 - acc: 0.8464Epoch 00612: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7536e-04 - acc: 0.8429 - val_loss: 0.0018 - val_acc: 0.8224
Epoch 614/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7856e-04 - acc: 0.8379Epoch 00613: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.8892e-04 - acc: 0.8318 - val_loss: 0.0022 - val_acc: 0.8061
Epoch 615/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.8532e-04 - acc: 0.8438Epoch 00614: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.8722e-04 - acc: 0.8400 - val_loss: 0.0020 - val_acc: 0.8224
Epoch 616/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.6693e-04 - acc: 0.8398Epoch 00615: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.6752e-04 - acc: 0.8382 - val_loss: 0.0021 - val_acc: 0.8201
Epoch 617/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7849e-04 - acc: 0.8249Epoch 00616: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.8583e-04 - acc: 0.8277 - val_loss: 0.0017 - val_acc: 0.8201
Epoch 618/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0307e-04 - acc: 0.8236Epoch 00617: val_loss improved from 0.00169 to 0.00164, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 6.9948e-04 - acc: 0.8195 - val_loss: 0.0016 - val_acc: 0.8224
Epoch 619/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 7.0190e-04 - acc: 0.8451Epoch 00618: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.9576e-04 - acc: 0.8417 - val_loss: 0.0019 - val_acc: 0.8061
Epoch 620/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.6331e-04 - acc: 0.8158Epoch 00619: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7875e-04 - acc: 0.8189 - val_loss: 0.0023 - val_acc: 0.8178
Epoch 621/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.9879e-04 - acc: 0.8522Epoch 00620: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.8959e-04 - acc: 0.8511 - val_loss: 0.0023 - val_acc: 0.8271
Epoch 622/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7458e-04 - acc: 0.8379Epoch 00621: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7697e-04 - acc: 0.8306 - val_loss: 0.0019 - val_acc: 0.8294
Epoch 623/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.6407e-04 - acc: 0.8503Epoch 00622: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.5767e-04 - acc: 0.8493 - val_loss: 0.0022 - val_acc: 0.8271
Epoch 624/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.7604e-04 - acc: 0.8464Epoch 00623: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7672e-04 - acc: 0.8470 - val_loss: 0.0018 - val_acc: 0.8364
Epoch 625/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.4279e-04 - acc: 0.8353Epoch 00624: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.4813e-04 - acc: 0.8359 - val_loss: 0.0016 - val_acc: 0.8084
Epoch 626/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.8049e-04 - acc: 0.8359Epoch 00625: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.7526e-04 - acc: 0.8376 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 627/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.4698e-04 - acc: 0.8262Epoch 00626: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.5112e-04 - acc: 0.8289 - val_loss: 0.0021 - val_acc: 0.8224
Epoch 628/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.5111e-04 - acc: 0.8340Epoch 00627: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.4606e-04 - acc: 0.8359 - val_loss: 0.0022 - val_acc: 0.8294
Epoch 629/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.5222e-04 - acc: 0.8314Epoch 00628: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.5620e-04 - acc: 0.8312 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 630/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2769e-04 - acc: 0.8529Epoch 00629: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2811e-04 - acc: 0.8470 - val_loss: 0.0020 - val_acc: 0.8248
Epoch 631/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2422e-04 - acc: 0.8359Epoch 00630: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2409e-04 - acc: 0.8400 - val_loss: 0.0020 - val_acc: 0.8248
Epoch 632/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2310e-04 - acc: 0.8464Epoch 00631: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.3041e-04 - acc: 0.8458 - val_loss: 0.0019 - val_acc: 0.8294
Epoch 633/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.3780e-04 - acc: 0.8431Epoch 00632: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.3701e-04 - acc: 0.8481 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 634/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2404e-04 - acc: 0.8333Epoch 00633: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2161e-04 - acc: 0.8312 - val_loss: 0.0018 - val_acc: 0.8178
Epoch 635/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.3303e-04 - acc: 0.8392Epoch 00634: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.3305e-04 - acc: 0.8376 - val_loss: 0.0022 - val_acc: 0.8224
Epoch 636/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2828e-04 - acc: 0.8333Epoch 00635: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2332e-04 - acc: 0.8329 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 637/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2487e-04 - acc: 0.8346Epoch 00636: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2481e-04 - acc: 0.8341 - val_loss: 0.0022 - val_acc: 0.8201
Epoch 638/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2223e-04 - acc: 0.8424Epoch 00637: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2233e-04 - acc: 0.8429 - val_loss: 0.0018 - val_acc: 0.8178
Epoch 639/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.3275e-04 - acc: 0.8444Epoch 00638: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2909e-04 - acc: 0.8475 - val_loss: 0.0018 - val_acc: 0.8201
Epoch 640/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.5368e-04 - acc: 0.8496Epoch 00639: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.5384e-04 - acc: 0.8446 - val_loss: 0.0020 - val_acc: 0.8224
Epoch 641/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.3204e-04 - acc: 0.8470Epoch 00640: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2980e-04 - acc: 0.8394 - val_loss: 0.0023 - val_acc: 0.8411
Epoch 642/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.5605e-04 - acc: 0.8320Epoch 00641: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.5293e-04 - acc: 0.8318 - val_loss: 0.0016 - val_acc: 0.8248
Epoch 643/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.4501e-04 - acc: 0.8535Epoch 00642: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.4960e-04 - acc: 0.8505 - val_loss: 0.0022 - val_acc: 0.8271
Epoch 644/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.4257e-04 - acc: 0.8405Epoch 00643: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.4220e-04 - acc: 0.8347 - val_loss: 0.0022 - val_acc: 0.8318
Epoch 645/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.1844e-04 - acc: 0.8457Epoch 00644: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.1764e-04 - acc: 0.8440 - val_loss: 0.0019 - val_acc: 0.8201
Epoch 646/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.0167e-04 - acc: 0.8516Epoch 00645: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0105e-04 - acc: 0.8487 - val_loss: 0.0017 - val_acc: 0.8178
Epoch 647/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.0578e-04 - acc: 0.8418Epoch 00646: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0706e-04 - acc: 0.8382 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 648/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9506e-04 - acc: 0.8431Epoch 00647: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9844e-04 - acc: 0.8423 - val_loss: 0.0021 - val_acc: 0.8131
Epoch 649/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.0290e-04 - acc: 0.8372Epoch 00648: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0130e-04 - acc: 0.8359 - val_loss: 0.0017 - val_acc: 0.8248
Epoch 650/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.0004e-04 - acc: 0.8385Epoch 00649: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0335e-04 - acc: 0.8382 - val_loss: 0.0021 - val_acc: 0.8248
Epoch 651/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9991e-04 - acc: 0.8470Epoch 00650: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0213e-04 - acc: 0.8475 - val_loss: 0.0017 - val_acc: 0.8248
Epoch 652/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2190e-04 - acc: 0.8477Epoch 00651: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2072e-04 - acc: 0.8470 - val_loss: 0.0017 - val_acc: 0.8224
Epoch 653/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.2960e-04 - acc: 0.8444Epoch 00652: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2420e-04 - acc: 0.8446 - val_loss: 0.0021 - val_acc: 0.8178
Epoch 654/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9252e-04 - acc: 0.8359Epoch 00653: val_loss improved from 0.00164 to 0.00157, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.9485e-04 - acc: 0.8347 - val_loss: 0.0016 - val_acc: 0.8248
Epoch 655/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.1946e-04 - acc: 0.8451Epoch 00654: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2764e-04 - acc: 0.8470 - val_loss: 0.0016 - val_acc: 0.8224
Epoch 656/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.1459e-04 - acc: 0.8529Epoch 00655: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.2173e-04 - acc: 0.8534 - val_loss: 0.0020 - val_acc: 0.8271
Epoch 657/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9984e-04 - acc: 0.8307Epoch 00656: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9657e-04 - acc: 0.8329 - val_loss: 0.0020 - val_acc: 0.8224
Epoch 658/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.8519e-04 - acc: 0.8555Epoch 00657: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9346e-04 - acc: 0.8487 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 659/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9263e-04 - acc: 0.8509Epoch 00658: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9601e-04 - acc: 0.8493 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 660/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.8730e-04 - acc: 0.8379Epoch 00659: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9337e-04 - acc: 0.8405 - val_loss: 0.0017 - val_acc: 0.8178
Epoch 661/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9167e-04 - acc: 0.8444Epoch 00660: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.8839e-04 - acc: 0.8464 - val_loss: 0.0017 - val_acc: 0.8294
Epoch 662/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7937e-04 - acc: 0.8359Epoch 00661: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.8268e-04 - acc: 0.8341 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 663/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7680e-04 - acc: 0.8411Epoch 00662: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7335e-04 - acc: 0.8405 - val_loss: 0.0018 - val_acc: 0.8201
Epoch 664/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7363e-04 - acc: 0.8483Epoch 00663: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7483e-04 - acc: 0.8452 - val_loss: 0.0021 - val_acc: 0.8271
Epoch 665/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.1051e-04 - acc: 0.8490Epoch 00664: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.1356e-04 - acc: 0.8522 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 666/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.9123e-04 - acc: 0.8594Epoch 00665: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.9341e-04 - acc: 0.8551 - val_loss: 0.0017 - val_acc: 0.8248
Epoch 667/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7778e-04 - acc: 0.8444Epoch 00666: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.8253e-04 - acc: 0.8493 - val_loss: 0.0019 - val_acc: 0.8294
Epoch 668/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7965e-04 - acc: 0.8516Epoch 00667: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7842e-04 - acc: 0.8522 - val_loss: 0.0018 - val_acc: 0.8294
Epoch 669/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6503e-04 - acc: 0.8366Epoch 00668: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6430e-04 - acc: 0.8411 - val_loss: 0.0017 - val_acc: 0.8224
Epoch 670/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.5473e-04 - acc: 0.8444Epoch 00669: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.5477e-04 - acc: 0.8458 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 671/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.5658e-04 - acc: 0.8431Epoch 00670: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6106e-04 - acc: 0.8435 - val_loss: 0.0019 - val_acc: 0.8271
Epoch 672/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7493e-04 - acc: 0.8490Epoch 00671: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7559e-04 - acc: 0.8458 - val_loss: 0.0017 - val_acc: 0.8248
Epoch 673/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.8456e-04 - acc: 0.8503Epoch 00672: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.8257e-04 - acc: 0.8470 - val_loss: 0.0020 - val_acc: 0.8248
Epoch 674/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7229e-04 - acc: 0.8379Epoch 00673: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6785e-04 - acc: 0.8400 - val_loss: 0.0018 - val_acc: 0.8154
Epoch 675/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7162e-04 - acc: 0.8503Epoch 00674: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6923e-04 - acc: 0.8522 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 676/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6415e-04 - acc: 0.8529Epoch 00675: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6158e-04 - acc: 0.8528 - val_loss: 0.0020 - val_acc: 0.8224
Epoch 677/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6076e-04 - acc: 0.8522Epoch 00676: val_loss improved from 0.00157 to 0.00157, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.6356e-04 - acc: 0.8487 - val_loss: 0.0016 - val_acc: 0.8154
Epoch 678/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6717e-04 - acc: 0.8424Epoch 00677: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6627e-04 - acc: 0.8423 - val_loss: 0.0018 - val_acc: 0.8224
Epoch 679/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4939e-04 - acc: 0.8620Epoch 00678: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.5232e-04 - acc: 0.8586 - val_loss: 0.0019 - val_acc: 0.8318
Epoch 680/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7057e-04 - acc: 0.8587Epoch 00679: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6626e-04 - acc: 0.8586 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 681/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7254e-04 - acc: 0.8470Epoch 00680: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6805e-04 - acc: 0.8540 - val_loss: 0.0016 - val_acc: 0.8294
Epoch 682/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7507e-04 - acc: 0.8561Epoch 00681: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7888e-04 - acc: 0.8575 - val_loss: 0.0021 - val_acc: 0.8341
Epoch 683/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7122e-04 - acc: 0.8516Epoch 00682: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7059e-04 - acc: 0.8551 - val_loss: 0.0022 - val_acc: 0.8341
Epoch 684/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 6.0827e-04 - acc: 0.8516Epoch 00683: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 6.0744e-04 - acc: 0.8540 - val_loss: 0.0020 - val_acc: 0.8061
Epoch 685/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.7708e-04 - acc: 0.8496Epoch 00684: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7256e-04 - acc: 0.8458 - val_loss: 0.0019 - val_acc: 0.8364
Epoch 686/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6435e-04 - acc: 0.8438Epoch 00685: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.6399e-04 - acc: 0.8481 - val_loss: 0.0019 - val_acc: 0.8084
Epoch 687/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6570e-04 - acc: 0.8464Epoch 00686: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.7381e-04 - acc: 0.8475 - val_loss: 0.0018 - val_acc: 0.8178
Epoch 688/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.5099e-04 - acc: 0.8405Epoch 00687: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.5063e-04 - acc: 0.8464 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 689/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3504e-04 - acc: 0.8411Epoch 00688: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3777e-04 - acc: 0.8446 - val_loss: 0.0017 - val_acc: 0.8294
Epoch 690/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4062e-04 - acc: 0.8516Epoch 00689: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3902e-04 - acc: 0.8534 - val_loss: 0.0018 - val_acc: 0.8294
Epoch 691/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4755e-04 - acc: 0.8477Epoch 00690: val_loss improved from 0.00157 to 0.00156, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.4311e-04 - acc: 0.8487 - val_loss: 0.0016 - val_acc: 0.8224
Epoch 692/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3843e-04 - acc: 0.8620Epoch 00691: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3716e-04 - acc: 0.8610 - val_loss: 0.0018 - val_acc: 0.8294
Epoch 693/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3886e-04 - acc: 0.8594Epoch 00692: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3875e-04 - acc: 0.8598 - val_loss: 0.0019 - val_acc: 0.8341
Epoch 694/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3520e-04 - acc: 0.8620Epoch 00693: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3514e-04 - acc: 0.8645 - val_loss: 0.0016 - val_acc: 0.8411
Epoch 695/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2974e-04 - acc: 0.8568Epoch 00694: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2868e-04 - acc: 0.8575 - val_loss: 0.0018 - val_acc: 0.8364
Epoch 696/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2300e-04 - acc: 0.8464Epoch 00695: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2796e-04 - acc: 0.8464 - val_loss: 0.0017 - val_acc: 0.8411
Epoch 697/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1936e-04 - acc: 0.8535Epoch 00696: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2308e-04 - acc: 0.8540 - val_loss: 0.0019 - val_acc: 0.8271
Epoch 698/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2410e-04 - acc: 0.8678Epoch 00697: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2400e-04 - acc: 0.8686 - val_loss: 0.0017 - val_acc: 0.8341
Epoch 699/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2406e-04 - acc: 0.8548Epoch 00698: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2183e-04 - acc: 0.8569 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 700/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1903e-04 - acc: 0.8659Epoch 00699: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1949e-04 - acc: 0.8692 - val_loss: 0.0017 - val_acc: 0.8201
Epoch 701/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2325e-04 - acc: 0.8431Epoch 00700: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2346e-04 - acc: 0.8452 - val_loss: 0.0018 - val_acc: 0.8224
Epoch 702/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4108e-04 - acc: 0.8626Epoch 00701: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3660e-04 - acc: 0.8639 - val_loss: 0.0020 - val_acc: 0.8294
Epoch 703/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6177e-04 - acc: 0.8470Epoch 00702: val_loss improved from 0.00156 to 0.00149, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.6286e-04 - acc: 0.8481 - val_loss: 0.0015 - val_acc: 0.8178
Epoch 704/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6015e-04 - acc: 0.8587Epoch 00703: val_loss improved from 0.00149 to 0.00147, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.5826e-04 - acc: 0.8575 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 705/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3791e-04 - acc: 0.8431Epoch 00704: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3583e-04 - acc: 0.8446 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 706/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.5375e-04 - acc: 0.8509Epoch 00705: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.5213e-04 - acc: 0.8511 - val_loss: 0.0019 - val_acc: 0.8341
Epoch 707/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4066e-04 - acc: 0.8529Epoch 00706: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3939e-04 - acc: 0.8546 - val_loss: 0.0020 - val_acc: 0.8388
Epoch 708/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.4350e-04 - acc: 0.8405Epoch 00707: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.4198e-04 - acc: 0.8435 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 709/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1735e-04 - acc: 0.8594Epoch 00708: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1998e-04 - acc: 0.8528 - val_loss: 0.0016 - val_acc: 0.8084
Epoch 710/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1279e-04 - acc: 0.8711Epoch 00709: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0911e-04 - acc: 0.8657 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 711/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.3576e-04 - acc: 0.8522Epoch 00710: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.3512e-04 - acc: 0.8516 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 712/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0540e-04 - acc: 0.8620Epoch 00711: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0547e-04 - acc: 0.8604 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 713/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1077e-04 - acc: 0.8561Epoch 00712: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1256e-04 - acc: 0.8546 - val_loss: 0.0016 - val_acc: 0.8178
Epoch 714/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2662e-04 - acc: 0.8607Epoch 00713: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2703e-04 - acc: 0.8592 - val_loss: 0.0019 - val_acc: 0.8341
Epoch 715/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1417e-04 - acc: 0.8594Epoch 00714: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1421e-04 - acc: 0.8604 - val_loss: 0.0019 - val_acc: 0.8364
Epoch 716/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1247e-04 - acc: 0.8600Epoch 00715: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1801e-04 - acc: 0.8569 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 717/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1685e-04 - acc: 0.8509Epoch 00716: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0999e-04 - acc: 0.8528 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 718/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0556e-04 - acc: 0.8516Epoch 00717: val_loss improved from 0.00147 to 0.00147, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 5.0531e-04 - acc: 0.8516 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 719/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1943e-04 - acc: 0.8542Epoch 00718: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1739e-04 - acc: 0.8563 - val_loss: 0.0017 - val_acc: 0.8411
Epoch 720/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0847e-04 - acc: 0.8503Epoch 00719: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1044e-04 - acc: 0.8493 - val_loss: 0.0023 - val_acc: 0.8294
Epoch 721/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.6369e-04 - acc: 0.8503Epoch 00720: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.5469e-04 - acc: 0.8528 - val_loss: 0.0020 - val_acc: 0.8341
Epoch 722/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.2121e-04 - acc: 0.8613Epoch 00721: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2058e-04 - acc: 0.8621 - val_loss: 0.0017 - val_acc: 0.8388
Epoch 723/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0884e-04 - acc: 0.8509Epoch 00722: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0489e-04 - acc: 0.8522 - val_loss: 0.0017 - val_acc: 0.8248
Epoch 724/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0431e-04 - acc: 0.8568Epoch 00723: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0162e-04 - acc: 0.8511 - val_loss: 0.0016 - val_acc: 0.8388
Epoch 725/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0414e-04 - acc: 0.8594Epoch 00724: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0068e-04 - acc: 0.8627 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 726/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.9477e-04 - acc: 0.8613Epoch 00725: val_loss improved from 0.00147 to 0.00141, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 4.9496e-04 - acc: 0.8592 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 727/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1805e-04 - acc: 0.8639Epoch 00726: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.2113e-04 - acc: 0.8621 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 728/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.0924e-04 - acc: 0.8548Epoch 00727: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0799e-04 - acc: 0.8586 - val_loss: 0.0018 - val_acc: 0.8364
Epoch 729/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1775e-04 - acc: 0.8516Epoch 00728: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1349e-04 - acc: 0.8575 - val_loss: 0.0020 - val_acc: 0.8364
Epoch 730/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1852e-04 - acc: 0.8594Epoch 00729: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1884e-04 - acc: 0.8598 - val_loss: 0.0019 - val_acc: 0.8364
Epoch 731/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1007e-04 - acc: 0.8509Epoch 00730: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0882e-04 - acc: 0.8522 - val_loss: 0.0018 - val_acc: 0.8341
Epoch 732/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8920e-04 - acc: 0.8665Epoch 00731: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8792e-04 - acc: 0.8645 - val_loss: 0.0017 - val_acc: 0.8341
Epoch 733/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8070e-04 - acc: 0.8581Epoch 00732: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7949e-04 - acc: 0.8610 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 734/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8959e-04 - acc: 0.8763Epoch 00733: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8712e-04 - acc: 0.8750 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 735/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8901e-04 - acc: 0.8665Epoch 00734: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8608e-04 - acc: 0.8657 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 736/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.9082e-04 - acc: 0.8704Epoch 00735: val_loss improved from 0.00141 to 0.00138, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 4.9224e-04 - acc: 0.8680 - val_loss: 0.0014 - val_acc: 0.8224
Epoch 737/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.9834e-04 - acc: 0.8607Epoch 00736: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.0017e-04 - acc: 0.8534 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 738/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8212e-04 - acc: 0.8659Epoch 00737: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8595e-04 - acc: 0.8674 - val_loss: 0.0020 - val_acc: 0.8341
Epoch 739/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 5.1236e-04 - acc: 0.8542Epoch 00738: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 5.1417e-04 - acc: 0.8557 - val_loss: 0.0017 - val_acc: 0.8294
Epoch 740/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7900e-04 - acc: 0.8639Epoch 00739: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7627e-04 - acc: 0.8645 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 741/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8447e-04 - acc: 0.8626Epoch 00740: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8696e-04 - acc: 0.8610 - val_loss: 0.0015 - val_acc: 0.8154
Epoch 742/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8506e-04 - acc: 0.8633Epoch 00741: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8435e-04 - acc: 0.8651 - val_loss: 0.0016 - val_acc: 0.8271
Epoch 743/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7510e-04 - acc: 0.8633Epoch 00742: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7454e-04 - acc: 0.8657 - val_loss: 0.0017 - val_acc: 0.8388
Epoch 744/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7169e-04 - acc: 0.8620Epoch 00743: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7197e-04 - acc: 0.8563 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 745/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7103e-04 - acc: 0.8626Epoch 00744: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7351e-04 - acc: 0.8610 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 746/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5957e-04 - acc: 0.8587Epoch 00745: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6184e-04 - acc: 0.8586 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 747/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8752e-04 - acc: 0.8542Epoch 00746: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8354e-04 - acc: 0.8516 - val_loss: 0.0018 - val_acc: 0.8318
Epoch 748/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8347e-04 - acc: 0.8581Epoch 00747: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8151e-04 - acc: 0.8604 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 749/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7906e-04 - acc: 0.8496Epoch 00748: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7831e-04 - acc: 0.8511 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 750/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7355e-04 - acc: 0.8509Epoch 00749: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7424e-04 - acc: 0.8511 - val_loss: 0.0016 - val_acc: 0.8411
Epoch 751/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6772e-04 - acc: 0.8659Epoch 00750: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6597e-04 - acc: 0.8662 - val_loss: 0.0015 - val_acc: 0.8435
Epoch 752/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7549e-04 - acc: 0.8607Epoch 00751: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7626e-04 - acc: 0.8592 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 753/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6466e-04 - acc: 0.8685Epoch 00752: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6585e-04 - acc: 0.8686 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 754/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6523e-04 - acc: 0.8704Epoch 00753: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6606e-04 - acc: 0.8662 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 755/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7004e-04 - acc: 0.8607Epoch 00754: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7246e-04 - acc: 0.8610 - val_loss: 0.0017 - val_acc: 0.8481
Epoch 756/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8165e-04 - acc: 0.8594Epoch 00755: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.7902e-04 - acc: 0.8581 - val_loss: 0.0018 - val_acc: 0.8388
Epoch 757/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6920e-04 - acc: 0.8652Epoch 00756: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6589e-04 - acc: 0.8633 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 758/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5918e-04 - acc: 0.8672Epoch 00757: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5834e-04 - acc: 0.8674 - val_loss: 0.0016 - val_acc: 0.8388
Epoch 759/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6086e-04 - acc: 0.8522Epoch 00758: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6207e-04 - acc: 0.8511 - val_loss: 0.0018 - val_acc: 0.8341
Epoch 760/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8422e-04 - acc: 0.8633Epoch 00759: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.9153e-04 - acc: 0.8621 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 761/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.9180e-04 - acc: 0.8704Epoch 00760: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.9878e-04 - acc: 0.8662 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 762/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.8901e-04 - acc: 0.8659Epoch 00761: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.8746e-04 - acc: 0.8662 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 763/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5553e-04 - acc: 0.8659Epoch 00762: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5396e-04 - acc: 0.8645 - val_loss: 0.0017 - val_acc: 0.8341
Epoch 764/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5178e-04 - acc: 0.8607Epoch 00763: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4888e-04 - acc: 0.8586 - val_loss: 0.0016 - val_acc: 0.8294
Epoch 765/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4468e-04 - acc: 0.8659Epoch 00764: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4976e-04 - acc: 0.8674 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 766/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5349e-04 - acc: 0.8685Epoch 00765: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5139e-04 - acc: 0.8721 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 767/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5961e-04 - acc: 0.8646Epoch 00766: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6056e-04 - acc: 0.8662 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 768/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5554e-04 - acc: 0.8691Epoch 00767: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5433e-04 - acc: 0.8674 - val_loss: 0.0016 - val_acc: 0.8294
Epoch 769/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4536e-04 - acc: 0.8665Epoch 00768: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4414e-04 - acc: 0.8686 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 770/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5048e-04 - acc: 0.8639Epoch 00769: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5014e-04 - acc: 0.8604 - val_loss: 0.0018 - val_acc: 0.8271
Epoch 771/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6166e-04 - acc: 0.8626Epoch 00770: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6088e-04 - acc: 0.8586 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 772/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6195e-04 - acc: 0.8678Epoch 00771: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6914e-04 - acc: 0.8686 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 773/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5970e-04 - acc: 0.8652Epoch 00772: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5577e-04 - acc: 0.8621 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 774/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5253e-04 - acc: 0.8529Epoch 00773: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5092e-04 - acc: 0.8499 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 775/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4197e-04 - acc: 0.8678Epoch 00774: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3922e-04 - acc: 0.8686 - val_loss: 0.0016 - val_acc: 0.8364
Epoch 776/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3349e-04 - acc: 0.8698Epoch 00775: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3364e-04 - acc: 0.8657 - val_loss: 0.0017 - val_acc: 0.8458
Epoch 777/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4098e-04 - acc: 0.8665Epoch 00776: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3873e-04 - acc: 0.8680 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 778/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4203e-04 - acc: 0.8822Epoch 00777: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4277e-04 - acc: 0.8803 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 779/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2952e-04 - acc: 0.8483Epoch 00778: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2992e-04 - acc: 0.8534 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 780/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2800e-04 - acc: 0.8665Epoch 00779: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2924e-04 - acc: 0.8662 - val_loss: 0.0017 - val_acc: 0.8318
Epoch 781/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3025e-04 - acc: 0.8665Epoch 00780: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3487e-04 - acc: 0.8680 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 782/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3953e-04 - acc: 0.8757Epoch 00781: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3974e-04 - acc: 0.8721 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 783/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5423e-04 - acc: 0.8659Epoch 00782: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5429e-04 - acc: 0.8604 - val_loss: 0.0016 - val_acc: 0.8271
Epoch 784/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.5236e-04 - acc: 0.8809Epoch 00783: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5183e-04 - acc: 0.8785 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 785/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4827e-04 - acc: 0.8665Epoch 00784: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4798e-04 - acc: 0.8633 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 786/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4679e-04 - acc: 0.8620Epoch 00785: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4733e-04 - acc: 0.8668 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 787/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3516e-04 - acc: 0.8691Epoch 00786: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3587e-04 - acc: 0.8703 - val_loss: 0.0016 - val_acc: 0.8248
Epoch 788/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4323e-04 - acc: 0.8620Epoch 00787: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4272e-04 - acc: 0.8657 - val_loss: 0.0019 - val_acc: 0.8248
Epoch 789/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.6227e-04 - acc: 0.8620Epoch 00788: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6050e-04 - acc: 0.8662 - val_loss: 0.0016 - val_acc: 0.8388
Epoch 790/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3250e-04 - acc: 0.8691Epoch 00789: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3224e-04 - acc: 0.8662 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 791/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2746e-04 - acc: 0.8678Epoch 00790: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2932e-04 - acc: 0.8616 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 792/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3422e-04 - acc: 0.8685Epoch 00791: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3862e-04 - acc: 0.8697 - val_loss: 0.0016 - val_acc: 0.8364
Epoch 793/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3607e-04 - acc: 0.8633Epoch 00792: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3844e-04 - acc: 0.8627 - val_loss: 0.0016 - val_acc: 0.8388
Epoch 794/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4807e-04 - acc: 0.8678Epoch 00793: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5032e-04 - acc: 0.8709 - val_loss: 0.0019 - val_acc: 0.8388
Epoch 795/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.7214e-04 - acc: 0.8737Epoch 00794: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.6786e-04 - acc: 0.8738 - val_loss: 0.0018 - val_acc: 0.8341
Epoch 796/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3672e-04 - acc: 0.8672Epoch 00795: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.3595e-04 - acc: 0.8697 - val_loss: 0.0018 - val_acc: 0.8341
Epoch 797/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3159e-04 - acc: 0.8626Epoch 00796: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2928e-04 - acc: 0.8621 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 798/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.3141e-04 - acc: 0.8724Epoch 00797: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2639e-04 - acc: 0.8738 - val_loss: 0.0016 - val_acc: 0.8411
Epoch 799/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1821e-04 - acc: 0.8600Epoch 00798: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1626e-04 - acc: 0.8633 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 800/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1524e-04 - acc: 0.8652Epoch 00799: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1567e-04 - acc: 0.8692 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 801/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1906e-04 - acc: 0.8815Epoch 00800: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1750e-04 - acc: 0.8861 - val_loss: 0.0016 - val_acc: 0.8435
Epoch 802/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1578e-04 - acc: 0.8835Epoch 00801: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1827e-04 - acc: 0.8808 - val_loss: 0.0016 - val_acc: 0.8224
Epoch 803/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1845e-04 - acc: 0.8633Epoch 00802: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1613e-04 - acc: 0.8657 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 804/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1371e-04 - acc: 0.8665Epoch 00803: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1477e-04 - acc: 0.8610 - val_loss: 0.0016 - val_acc: 0.8271
Epoch 805/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2285e-04 - acc: 0.8724Epoch 00804: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2187e-04 - acc: 0.8727 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 806/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1610e-04 - acc: 0.8717Epoch 00805: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1670e-04 - acc: 0.8756 - val_loss: 0.0015 - val_acc: 0.8201
Epoch 807/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1959e-04 - acc: 0.8672Epoch 00806: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1696e-04 - acc: 0.8697 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 808/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1663e-04 - acc: 0.8730Epoch 00807: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1608e-04 - acc: 0.8715 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 809/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1625e-04 - acc: 0.8724Epoch 00808: val_loss improved from 0.00138 to 0.00135, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 4.1822e-04 - acc: 0.8750 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 810/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2422e-04 - acc: 0.8704Epoch 00809: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2192e-04 - acc: 0.8680 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 811/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1931e-04 - acc: 0.8568Epoch 00810: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1860e-04 - acc: 0.8563 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 812/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0373e-04 - acc: 0.8594Epoch 00811: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0423e-04 - acc: 0.8621 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 813/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1236e-04 - acc: 0.8704Epoch 00812: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1601e-04 - acc: 0.8750 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 814/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1432e-04 - acc: 0.8763Epoch 00813: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1510e-04 - acc: 0.8762 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 815/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4404e-04 - acc: 0.8743Epoch 00814: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4908e-04 - acc: 0.8744 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 816/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4462e-04 - acc: 0.8730Epoch 00815: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.5220e-04 - acc: 0.8727 - val_loss: 0.0016 - val_acc: 0.8435
Epoch 817/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.4083e-04 - acc: 0.8698Epoch 00816: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.4625e-04 - acc: 0.8744 - val_loss: 0.0014 - val_acc: 0.8435
Epoch 818/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2391e-04 - acc: 0.8796Epoch 00817: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2547e-04 - acc: 0.8779 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 819/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1356e-04 - acc: 0.8672Epoch 00818: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1398e-04 - acc: 0.8668 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 820/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1327e-04 - acc: 0.8757Epoch 00819: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1356e-04 - acc: 0.8727 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 821/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1199e-04 - acc: 0.8685Epoch 00820: val_loss improved from 0.00135 to 0.00131, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 4.1435e-04 - acc: 0.8674 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 822/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1628e-04 - acc: 0.8646Epoch 00821: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1736e-04 - acc: 0.8657 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 823/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1743e-04 - acc: 0.8691Epoch 00822: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1796e-04 - acc: 0.8662 - val_loss: 0.0015 - val_acc: 0.8435
Epoch 824/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9994e-04 - acc: 0.8730Epoch 00823: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0288e-04 - acc: 0.8715 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 825/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0161e-04 - acc: 0.8835Epoch 00824: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0215e-04 - acc: 0.8808 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 826/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0805e-04 - acc: 0.8613Epoch 00825: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1003e-04 - acc: 0.8616 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 827/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0067e-04 - acc: 0.8685Epoch 00826: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0211e-04 - acc: 0.8680 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 828/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1316e-04 - acc: 0.8659Epoch 00827: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0892e-04 - acc: 0.8651 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 829/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1075e-04 - acc: 0.8763Epoch 00828: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0825e-04 - acc: 0.8768 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 830/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0254e-04 - acc: 0.8809Epoch 00829: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0330e-04 - acc: 0.8861 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 831/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0071e-04 - acc: 0.8678Epoch 00830: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0101e-04 - acc: 0.8686 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 832/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0202e-04 - acc: 0.8789Epoch 00831: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0573e-04 - acc: 0.8826 - val_loss: 0.0014 - val_acc: 0.8201
Epoch 833/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0371e-04 - acc: 0.8893Epoch 00832: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0258e-04 - acc: 0.8855 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 834/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9752e-04 - acc: 0.8639Epoch 00833: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9849e-04 - acc: 0.8662 - val_loss: 0.0016 - val_acc: 0.8411
Epoch 835/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9959e-04 - acc: 0.8815Epoch 00834: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0023e-04 - acc: 0.8814 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 836/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9477e-04 - acc: 0.8783Epoch 00835: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9632e-04 - acc: 0.8808 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 837/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8958e-04 - acc: 0.8685Epoch 00836: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9158e-04 - acc: 0.8692 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 838/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0121e-04 - acc: 0.8757Epoch 00837: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0093e-04 - acc: 0.8738 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 839/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9139e-04 - acc: 0.8848Epoch 00838: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9140e-04 - acc: 0.8867 - val_loss: 0.0015 - val_acc: 0.8411
Epoch 840/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9475e-04 - acc: 0.8724Epoch 00839: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9516e-04 - acc: 0.8779 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 841/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9551e-04 - acc: 0.8828Epoch 00840: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9633e-04 - acc: 0.8826 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 842/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9404e-04 - acc: 0.8743Epoch 00841: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9506e-04 - acc: 0.8738 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 843/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8881e-04 - acc: 0.8711Epoch 00842: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9014e-04 - acc: 0.8715 - val_loss: 0.0018 - val_acc: 0.8364
Epoch 844/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2065e-04 - acc: 0.8809Epoch 00843: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2409e-04 - acc: 0.8768 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 845/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1840e-04 - acc: 0.8763Epoch 00844: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.1555e-04 - acc: 0.8773 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 846/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0690e-04 - acc: 0.8750Epoch 00845: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0830e-04 - acc: 0.8762 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 847/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9647e-04 - acc: 0.8750Epoch 00846: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9742e-04 - acc: 0.8756 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 848/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8424e-04 - acc: 0.8796Epoch 00847: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8767e-04 - acc: 0.8820 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 849/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8331e-04 - acc: 0.8743Epoch 00848: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8479e-04 - acc: 0.8744 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 850/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8469e-04 - acc: 0.8776Epoch 00849: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8460e-04 - acc: 0.8797 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 851/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9256e-04 - acc: 0.8659Epoch 00850: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9439e-04 - acc: 0.8668 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 852/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9289e-04 - acc: 0.8880Epoch 00851: val_loss improved from 0.00131 to 0.00122, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.9123e-04 - acc: 0.8843 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 853/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.0504e-04 - acc: 0.8776Epoch 00852: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0865e-04 - acc: 0.8779 - val_loss: 0.0015 - val_acc: 0.8435
Epoch 854/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9967e-04 - acc: 0.8730Epoch 00853: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0476e-04 - acc: 0.8709 - val_loss: 0.0017 - val_acc: 0.8388
Epoch 855/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.2382e-04 - acc: 0.8620Epoch 00854: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.2052e-04 - acc: 0.8639 - val_loss: 0.0017 - val_acc: 0.8341
Epoch 856/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 4.1253e-04 - acc: 0.8776Epoch 00855: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 4.0971e-04 - acc: 0.8808 - val_loss: 0.0017 - val_acc: 0.8364
Epoch 857/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9539e-04 - acc: 0.8835Epoch 00856: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9559e-04 - acc: 0.8838 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 858/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8306e-04 - acc: 0.8659Epoch 00857: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8311e-04 - acc: 0.8715 - val_loss: 0.0017 - val_acc: 0.8271
Epoch 859/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9926e-04 - acc: 0.8730Epoch 00858: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9455e-04 - acc: 0.8721 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 860/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7230e-04 - acc: 0.8770Epoch 00859: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7371e-04 - acc: 0.8785 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 861/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8153e-04 - acc: 0.8841Epoch 00860: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8135e-04 - acc: 0.8849 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 862/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8791e-04 - acc: 0.8652Epoch 00861: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8398e-04 - acc: 0.8662 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 863/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8324e-04 - acc: 0.8815Epoch 00862: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7965e-04 - acc: 0.8843 - val_loss: 0.0013 - val_acc: 0.8248
Epoch 864/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8222e-04 - acc: 0.8783Epoch 00863: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8147e-04 - acc: 0.8773 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 865/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8709e-04 - acc: 0.8900Epoch 00864: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8654e-04 - acc: 0.8849 - val_loss: 0.0016 - val_acc: 0.8364
Epoch 866/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8812e-04 - acc: 0.8704Epoch 00865: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8961e-04 - acc: 0.8738 - val_loss: 0.0016 - val_acc: 0.8364
Epoch 867/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9502e-04 - acc: 0.8737Epoch 00866: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9512e-04 - acc: 0.8738 - val_loss: 0.0016 - val_acc: 0.8341
Epoch 868/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9792e-04 - acc: 0.8913Epoch 00867: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9842e-04 - acc: 0.8908 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 869/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8890e-04 - acc: 0.8665Epoch 00868: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8811e-04 - acc: 0.8709 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 870/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9956e-04 - acc: 0.8906Epoch 00869: val_loss improved from 0.00122 to 0.00120, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.9791e-04 - acc: 0.8890 - val_loss: 0.0012 - val_acc: 0.8481
Epoch 871/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9304e-04 - acc: 0.8848Epoch 00870: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9175e-04 - acc: 0.8879 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 872/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7733e-04 - acc: 0.8848Epoch 00871: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7514e-04 - acc: 0.8867 - val_loss: 0.0014 - val_acc: 0.8271
Epoch 873/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7728e-04 - acc: 0.8926Epoch 00872: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7828e-04 - acc: 0.8902 - val_loss: 0.0016 - val_acc: 0.8388
Epoch 874/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7951e-04 - acc: 0.8815Epoch 00873: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7686e-04 - acc: 0.8814 - val_loss: 0.0015 - val_acc: 0.8248
Epoch 875/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6986e-04 - acc: 0.8763Epoch 00874: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7111e-04 - acc: 0.8738 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 876/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9933e-04 - acc: 0.8770Epoch 00875: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9783e-04 - acc: 0.8791 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 877/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6592e-04 - acc: 0.8809Epoch 00876: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6649e-04 - acc: 0.8803 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 878/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6808e-04 - acc: 0.8861Epoch 00877: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7294e-04 - acc: 0.8814 - val_loss: 0.0014 - val_acc: 0.8435
Epoch 879/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7174e-04 - acc: 0.8815Epoch 00878: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7316e-04 - acc: 0.8797 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 880/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7218e-04 - acc: 0.8717Epoch 00879: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7170e-04 - acc: 0.8779 - val_loss: 0.0015 - val_acc: 0.8294
Epoch 881/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7298e-04 - acc: 0.8828Epoch 00880: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7187e-04 - acc: 0.8826 - val_loss: 0.0016 - val_acc: 0.8364
Epoch 882/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7374e-04 - acc: 0.8750Epoch 00881: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7196e-04 - acc: 0.8791 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 883/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7722e-04 - acc: 0.8639Epoch 00882: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7650e-04 - acc: 0.8680 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 884/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7928e-04 - acc: 0.8802Epoch 00883: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8151e-04 - acc: 0.8738 - val_loss: 0.0015 - val_acc: 0.8411
Epoch 885/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7218e-04 - acc: 0.8926Epoch 00884: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7219e-04 - acc: 0.8943 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 886/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7786e-04 - acc: 0.8757Epoch 00885: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7563e-04 - acc: 0.8779 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 887/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7360e-04 - acc: 0.8757Epoch 00886: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7257e-04 - acc: 0.8756 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 888/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7226e-04 - acc: 0.8730Epoch 00887: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7232e-04 - acc: 0.8750 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 889/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6265e-04 - acc: 0.8854Epoch 00888: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6461e-04 - acc: 0.8791 - val_loss: 0.0015 - val_acc: 0.8458
Epoch 890/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6678e-04 - acc: 0.8822Epoch 00889: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6859e-04 - acc: 0.8832 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 891/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6875e-04 - acc: 0.8867Epoch 00890: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7015e-04 - acc: 0.8838 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 892/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7362e-04 - acc: 0.8809Epoch 00891: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6964e-04 - acc: 0.8808 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 893/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6325e-04 - acc: 0.8848Epoch 00892: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6708e-04 - acc: 0.8849 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 894/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.8007e-04 - acc: 0.8822Epoch 00893: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.8162e-04 - acc: 0.8808 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 895/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5839e-04 - acc: 0.8835Epoch 00894: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5868e-04 - acc: 0.8855 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 896/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.9173e-04 - acc: 0.8796Epoch 00895: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.9609e-04 - acc: 0.8826 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 897/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7337e-04 - acc: 0.8815Epoch 00896: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7491e-04 - acc: 0.8803 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 898/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7012e-04 - acc: 0.8822Epoch 00897: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7025e-04 - acc: 0.8785 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 899/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6931e-04 - acc: 0.8809Epoch 00898: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6836e-04 - acc: 0.8803 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 900/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6796e-04 - acc: 0.8757Epoch 00899: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6678e-04 - acc: 0.8744 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 901/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6201e-04 - acc: 0.8763Epoch 00900: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6384e-04 - acc: 0.8762 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 902/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5690e-04 - acc: 0.8796Epoch 00901: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5755e-04 - acc: 0.8855 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 903/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5108e-04 - acc: 0.8737Epoch 00902: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5165e-04 - acc: 0.8727 - val_loss: 0.0015 - val_acc: 0.8364
Epoch 904/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5398e-04 - acc: 0.8939Epoch 00903: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5564e-04 - acc: 0.8978 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 905/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5805e-04 - acc: 0.8796Epoch 00904: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5686e-04 - acc: 0.8814 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 906/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6797e-04 - acc: 0.8711Epoch 00905: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6493e-04 - acc: 0.8703 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 907/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5354e-04 - acc: 0.8848Epoch 00906: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5667e-04 - acc: 0.8873 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 908/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5260e-04 - acc: 0.8900Epoch 00907: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5254e-04 - acc: 0.8896 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 909/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5757e-04 - acc: 0.8835Epoch 00908: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5745e-04 - acc: 0.8838 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 910/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6063e-04 - acc: 0.8763Epoch 00909: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5931e-04 - acc: 0.8738 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 911/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5091e-04 - acc: 0.8939Epoch 00910: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5072e-04 - acc: 0.8879 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 912/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4526e-04 - acc: 0.8919Epoch 00911: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4837e-04 - acc: 0.8931 - val_loss: 0.0013 - val_acc: 0.8248
Epoch 913/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6404e-04 - acc: 0.8743Epoch 00912: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6472e-04 - acc: 0.8738 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 914/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6264e-04 - acc: 0.8809Epoch 00913: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5944e-04 - acc: 0.8803 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 915/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4774e-04 - acc: 0.8763Epoch 00914: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4801e-04 - acc: 0.8768 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 916/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5871e-04 - acc: 0.8750Epoch 00915: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5797e-04 - acc: 0.8791 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 917/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6015e-04 - acc: 0.8822Epoch 00916: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5807e-04 - acc: 0.8814 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 918/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5138e-04 - acc: 0.8880Epoch 00917: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4935e-04 - acc: 0.8884 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 919/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4355e-04 - acc: 0.8763Epoch 00918: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4136e-04 - acc: 0.8791 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 920/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5598e-04 - acc: 0.8939Epoch 00919: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5795e-04 - acc: 0.8902 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 921/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4827e-04 - acc: 0.8854Epoch 00920: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4960e-04 - acc: 0.8826 - val_loss: 0.0015 - val_acc: 0.8411
Epoch 922/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5147e-04 - acc: 0.8711Epoch 00921: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5171e-04 - acc: 0.8674 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 923/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6417e-04 - acc: 0.8770Epoch 00922: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6305e-04 - acc: 0.8791 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 924/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5714e-04 - acc: 0.8783Epoch 00923: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5821e-04 - acc: 0.8773 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 925/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6445e-04 - acc: 0.8880Epoch 00924: val_loss improved from 0.00120 to 0.00116, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.6342e-04 - acc: 0.8843 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 926/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.7326e-04 - acc: 0.8776Epoch 00925: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.7240e-04 - acc: 0.8768 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 927/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4634e-04 - acc: 0.8815Epoch 00926: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4738e-04 - acc: 0.8803 - val_loss: 0.0014 - val_acc: 0.8481
Epoch 928/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4962e-04 - acc: 0.8835Epoch 00927: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4882e-04 - acc: 0.8884 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 929/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5030e-04 - acc: 0.8802Epoch 00928: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5003e-04 - acc: 0.8773 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 930/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5449e-04 - acc: 0.8958Epoch 00929: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5202e-04 - acc: 0.8966 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 931/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4345e-04 - acc: 0.8932Epoch 00930: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4469e-04 - acc: 0.8931 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 932/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4495e-04 - acc: 0.8919Epoch 00931: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4666e-04 - acc: 0.8919 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 933/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4105e-04 - acc: 0.8952Epoch 00932: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4382e-04 - acc: 0.8919 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 934/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4378e-04 - acc: 0.8770Epoch 00933: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4476e-04 - acc: 0.8791 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 935/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4577e-04 - acc: 0.8848Epoch 00934: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4766e-04 - acc: 0.8838 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 936/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3924e-04 - acc: 0.8893Epoch 00935: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4451e-04 - acc: 0.8855 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 937/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3836e-04 - acc: 0.8809Epoch 00936: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3569e-04 - acc: 0.8826 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 938/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4073e-04 - acc: 0.8874Epoch 00937: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3936e-04 - acc: 0.8879 - val_loss: 0.0014 - val_acc: 0.8271
Epoch 939/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3907e-04 - acc: 0.8796Epoch 00938: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3874e-04 - acc: 0.8768 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 940/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3533e-04 - acc: 0.8913Epoch 00939: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3865e-04 - acc: 0.8908 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 941/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4135e-04 - acc: 0.8809Epoch 00940: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4328e-04 - acc: 0.8820 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 942/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4974e-04 - acc: 0.8867Epoch 00941: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4964e-04 - acc: 0.8879 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 943/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4866e-04 - acc: 0.8822Epoch 00942: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4839e-04 - acc: 0.8791 - val_loss: 0.0013 - val_acc: 0.8248
Epoch 944/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3928e-04 - acc: 0.8763Epoch 00943: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4232e-04 - acc: 0.8773 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 945/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4859e-04 - acc: 0.8809Epoch 00944: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4643e-04 - acc: 0.8808 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 946/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4585e-04 - acc: 0.8874Epoch 00945: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4400e-04 - acc: 0.8867 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 947/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.6398e-04 - acc: 0.8822Epoch 00946: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6017e-04 - acc: 0.8820 - val_loss: 0.0012 - val_acc: 0.8201
Epoch 948/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5221e-04 - acc: 0.8978Epoch 00947: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5435e-04 - acc: 0.9013 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 949/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4865e-04 - acc: 0.8893Epoch 00948: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5023e-04 - acc: 0.8873 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 950/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3919e-04 - acc: 0.8880Epoch 00949: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3940e-04 - acc: 0.8861 - val_loss: 0.0015 - val_acc: 0.8481
Epoch 951/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4811e-04 - acc: 0.8815Epoch 00950: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4905e-04 - acc: 0.8867 - val_loss: 0.0016 - val_acc: 0.8318
Epoch 952/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5418e-04 - acc: 0.8984Epoch 00951: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.5186e-04 - acc: 0.8943 - val_loss: 0.0015 - val_acc: 0.8224
Epoch 953/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3802e-04 - acc: 0.8926Epoch 00952: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3724e-04 - acc: 0.8931 - val_loss: 0.0015 - val_acc: 0.8318
Epoch 954/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3963e-04 - acc: 0.8854Epoch 00953: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3965e-04 - acc: 0.8861 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 955/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3864e-04 - acc: 0.8913Epoch 00954: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3746e-04 - acc: 0.8914 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 956/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.5873e-04 - acc: 0.8971Epoch 00955: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.6063e-04 - acc: 0.8978 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 957/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4906e-04 - acc: 0.8743Epoch 00956: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4993e-04 - acc: 0.8791 - val_loss: 0.0013 - val_acc: 0.8528
Epoch 958/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4647e-04 - acc: 0.8691Epoch 00957: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4713e-04 - acc: 0.8738 - val_loss: 0.0013 - val_acc: 0.8481
Epoch 959/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4789e-04 - acc: 0.8880Epoch 00958: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4359e-04 - acc: 0.8896 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 960/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3233e-04 - acc: 0.8874Epoch 00959: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3339e-04 - acc: 0.8861 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 961/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3165e-04 - acc: 0.8906Epoch 00960: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3402e-04 - acc: 0.8908 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 962/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4004e-04 - acc: 0.8802Epoch 00961: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3632e-04 - acc: 0.8814 - val_loss: 0.0012 - val_acc: 0.8481
Epoch 963/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3050e-04 - acc: 0.8763Epoch 00962: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3194e-04 - acc: 0.8803 - val_loss: 0.0013 - val_acc: 0.8224
Epoch 964/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2722e-04 - acc: 0.8880Epoch 00963: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2750e-04 - acc: 0.8884 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 965/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3572e-04 - acc: 0.8802Epoch 00964: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3476e-04 - acc: 0.8808 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 966/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2933e-04 - acc: 0.8939Epoch 00965: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2826e-04 - acc: 0.8914 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 967/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3445e-04 - acc: 0.8848Epoch 00966: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3444e-04 - acc: 0.8861 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 968/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2852e-04 - acc: 0.8757Epoch 00967: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2937e-04 - acc: 0.8762 - val_loss: 0.0013 - val_acc: 0.8481
Epoch 969/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2832e-04 - acc: 0.8867Epoch 00968: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3074e-04 - acc: 0.8873 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 970/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3678e-04 - acc: 0.8861Epoch 00969: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3607e-04 - acc: 0.8861 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 971/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2349e-04 - acc: 0.8796Epoch 00970: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2444e-04 - acc: 0.8820 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 972/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3754e-04 - acc: 0.8861Epoch 00971: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3580e-04 - acc: 0.8832 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 973/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2432e-04 - acc: 0.8880Epoch 00972: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2402e-04 - acc: 0.8896 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 974/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3387e-04 - acc: 0.8919Epoch 00973: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3524e-04 - acc: 0.8919 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 975/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2292e-04 - acc: 0.9017Epoch 00974: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2098e-04 - acc: 0.9030 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 976/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1832e-04 - acc: 0.8854Epoch 00975: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2061e-04 - acc: 0.8890 - val_loss: 0.0013 - val_acc: 0.8201
Epoch 977/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2033e-04 - acc: 0.8978Epoch 00976: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2101e-04 - acc: 0.8919 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 978/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1269e-04 - acc: 0.8822Epoch 00977: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1296e-04 - acc: 0.8808 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 979/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2277e-04 - acc: 0.8919Epoch 00978: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2561e-04 - acc: 0.8867 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 980/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3545e-04 - acc: 0.8978Epoch 00979: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3543e-04 - acc: 0.8972 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 981/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3374e-04 - acc: 0.8874Epoch 00980: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3378e-04 - acc: 0.8849 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 982/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2685e-04 - acc: 0.8971Epoch 00981: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2508e-04 - acc: 0.8989 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 983/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2672e-04 - acc: 0.8874Epoch 00982: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2916e-04 - acc: 0.8873 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 984/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2033e-04 - acc: 0.8919Epoch 00983: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1777e-04 - acc: 0.8914 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 985/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1939e-04 - acc: 0.8991Epoch 00984: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2092e-04 - acc: 0.8943 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 986/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.3331e-04 - acc: 0.8874Epoch 00985: val_loss improved from 0.00116 to 0.00114, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.3143e-04 - acc: 0.8849 - val_loss: 0.0011 - val_acc: 0.8341
Epoch 987/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.4985e-04 - acc: 0.8893Epoch 00986: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.4688e-04 - acc: 0.8896 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 988/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2341e-04 - acc: 0.8893Epoch 00987: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2378e-04 - acc: 0.8902 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 989/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1822e-04 - acc: 0.8867Epoch 00988: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1722e-04 - acc: 0.8873 - val_loss: 0.0014 - val_acc: 0.8435
Epoch 990/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2505e-04 - acc: 0.8861Epoch 00989: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2408e-04 - acc: 0.8855 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 991/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2173e-04 - acc: 0.8828Epoch 00990: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2038e-04 - acc: 0.8832 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 992/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2485e-04 - acc: 0.8932Epoch 00991: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2225e-04 - acc: 0.8925 - val_loss: 0.0015 - val_acc: 0.8341
Epoch 993/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2288e-04 - acc: 0.8874Epoch 00992: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2471e-04 - acc: 0.8855 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 994/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2661e-04 - acc: 0.8861Epoch 00993: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2515e-04 - acc: 0.8879 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 995/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1517e-04 - acc: 0.8971Epoch 00994: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1690e-04 - acc: 0.8943 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 996/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1243e-04 - acc: 0.8945Epoch 00995: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1182e-04 - acc: 0.8972 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 997/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1851e-04 - acc: 0.8893Epoch 00996: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2062e-04 - acc: 0.8861 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 998/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2797e-04 - acc: 0.8887Epoch 00997: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2865e-04 - acc: 0.8914 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 999/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2600e-04 - acc: 0.8971Epoch 00998: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2577e-04 - acc: 0.8984 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 1000/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2267e-04 - acc: 0.9010Epoch 00999: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2225e-04 - acc: 0.9001 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 1001/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1552e-04 - acc: 0.8926Epoch 01000: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1895e-04 - acc: 0.8937 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1002/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1755e-04 - acc: 0.8952Epoch 01001: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1722e-04 - acc: 0.8919 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1003/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1851e-04 - acc: 0.8919Epoch 01002: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1786e-04 - acc: 0.8908 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1004/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1510e-04 - acc: 0.8848Epoch 01003: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1685e-04 - acc: 0.8803 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1005/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1603e-04 - acc: 0.8880Epoch 01004: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1673e-04 - acc: 0.8890 - val_loss: 0.0015 - val_acc: 0.8481
Epoch 1006/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1532e-04 - acc: 0.8932Epoch 01005: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1721e-04 - acc: 0.8937 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1007/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2109e-04 - acc: 0.8997Epoch 01006: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2210e-04 - acc: 0.8949 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1008/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1551e-04 - acc: 0.8919Epoch 01007: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1525e-04 - acc: 0.8937 - val_loss: 0.0015 - val_acc: 0.8271
Epoch 1009/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1444e-04 - acc: 0.8789Epoch 01008: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1134e-04 - acc: 0.8762 - val_loss: 0.0014 - val_acc: 0.8201
Epoch 1010/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1704e-04 - acc: 0.8952Epoch 01009: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1838e-04 - acc: 0.8949 - val_loss: 0.0012 - val_acc: 0.8435
Epoch 1011/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1465e-04 - acc: 0.9036Epoch 01010: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1532e-04 - acc: 0.9007 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1012/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1485e-04 - acc: 0.9004Epoch 01011: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1748e-04 - acc: 0.9007 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 1013/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1199e-04 - acc: 0.9069Epoch 01012: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1224e-04 - acc: 0.9060 - val_loss: 0.0014 - val_acc: 0.8364
Epoch 1014/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0990e-04 - acc: 0.8971Epoch 01013: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1073e-04 - acc: 0.8949 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1015/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0972e-04 - acc: 0.8796Epoch 01014: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1044e-04 - acc: 0.8779 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1016/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0749e-04 - acc: 0.8913Epoch 01015: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0655e-04 - acc: 0.8943 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1017/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0935e-04 - acc: 0.8978Epoch 01016: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0608e-04 - acc: 0.9019 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1018/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0295e-04 - acc: 0.8880Epoch 01017: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0425e-04 - acc: 0.8919 - val_loss: 0.0011 - val_acc: 0.8271
Epoch 1019/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2761e-04 - acc: 0.8887Epoch 01018: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2375e-04 - acc: 0.8879 - val_loss: 0.0014 - val_acc: 0.8224
Epoch 1020/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1703e-04 - acc: 0.9010Epoch 01019: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1712e-04 - acc: 0.9007 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1021/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1176e-04 - acc: 0.8841Epoch 01020: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1086e-04 - acc: 0.8884 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1022/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0534e-04 - acc: 0.9004Epoch 01021: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0491e-04 - acc: 0.9001 - val_loss: 0.0013 - val_acc: 0.8481
Epoch 1023/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0643e-04 - acc: 0.8861Epoch 01022: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0665e-04 - acc: 0.8820 - val_loss: 0.0012 - val_acc: 0.8458
Epoch 1024/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1222e-04 - acc: 0.9017Epoch 01023: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1494e-04 - acc: 0.9019 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1025/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2666e-04 - acc: 0.8880Epoch 01024: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.3152e-04 - acc: 0.8884 - val_loss: 0.0013 - val_acc: 0.8178
Epoch 1026/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2215e-04 - acc: 0.8926Epoch 01025: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2371e-04 - acc: 0.8943 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1027/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2732e-04 - acc: 0.8958Epoch 01026: val_loss improved from 0.00114 to 0.00114, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.2684e-04 - acc: 0.8954 - val_loss: 0.0011 - val_acc: 0.8154
Epoch 1028/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.2442e-04 - acc: 0.8789Epoch 01027: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.2389e-04 - acc: 0.8808 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1029/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1894e-04 - acc: 0.8939Epoch 01028: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1781e-04 - acc: 0.8925 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1030/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1172e-04 - acc: 0.8887Epoch 01029: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1217e-04 - acc: 0.8896 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1031/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1334e-04 - acc: 0.8789Epoch 01030: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1312e-04 - acc: 0.8849 - val_loss: 0.0013 - val_acc: 0.8458
Epoch 1032/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1026e-04 - acc: 0.8867Epoch 01031: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0931e-04 - acc: 0.8902 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1033/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0588e-04 - acc: 0.8874Epoch 01032: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0514e-04 - acc: 0.8849 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1034/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0456e-04 - acc: 0.9017Epoch 01033: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0974e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1035/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0325e-04 - acc: 0.8978Epoch 01034: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0391e-04 - acc: 0.8949 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1036/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0791e-04 - acc: 0.8841Epoch 01035: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0713e-04 - acc: 0.8890 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1037/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1268e-04 - acc: 0.8887Epoch 01036: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1217e-04 - acc: 0.8914 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1038/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0912e-04 - acc: 0.8978Epoch 01037: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1030e-04 - acc: 0.8984 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1039/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0609e-04 - acc: 0.9004Epoch 01038: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0478e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1040/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0352e-04 - acc: 0.8717Epoch 01039: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0192e-04 - acc: 0.8762 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1041/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0371e-04 - acc: 0.8958Epoch 01040: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0533e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1042/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0958e-04 - acc: 0.8984Epoch 01041: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1052e-04 - acc: 0.9054 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1043/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9591e-04 - acc: 0.8900Epoch 01042: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9648e-04 - acc: 0.8931 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1044/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9691e-04 - acc: 0.8932Epoch 01043: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9669e-04 - acc: 0.8914 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1045/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0493e-04 - acc: 0.8854Epoch 01044: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0502e-04 - acc: 0.8838 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1046/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0322e-04 - acc: 0.8867Epoch 01045: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0129e-04 - acc: 0.8873 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1047/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9702e-04 - acc: 0.8965Epoch 01046: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9606e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1048/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9554e-04 - acc: 0.9049Epoch 01047: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9606e-04 - acc: 0.9013 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1049/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9915e-04 - acc: 0.8997Epoch 01048: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9822e-04 - acc: 0.8984 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1050/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9819e-04 - acc: 0.8828Epoch 01049: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9729e-04 - acc: 0.8890 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1051/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9920e-04 - acc: 0.8900Epoch 01050: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9601e-04 - acc: 0.8896 - val_loss: 0.0014 - val_acc: 0.8411
Epoch 1052/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1348e-04 - acc: 0.8815Epoch 01051: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1199e-04 - acc: 0.8820 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1053/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0169e-04 - acc: 0.9089Epoch 01052: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0564e-04 - acc: 0.9095 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1054/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1061e-04 - acc: 0.8880Epoch 01053: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0700e-04 - acc: 0.8914 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 1055/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0071e-04 - acc: 0.8887Epoch 01054: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9929e-04 - acc: 0.8879 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1056/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9968e-04 - acc: 0.8952Epoch 01055: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9924e-04 - acc: 0.8931 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1057/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9395e-04 - acc: 0.8880Epoch 01056: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9573e-04 - acc: 0.8867 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1058/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9352e-04 - acc: 0.8965Epoch 01057: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9435e-04 - acc: 0.8925 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 1059/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0481e-04 - acc: 0.8978Epoch 01058: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0468e-04 - acc: 0.9001 - val_loss: 0.0015 - val_acc: 0.8388
Epoch 1060/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.1517e-04 - acc: 0.8945Epoch 01059: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1309e-04 - acc: 0.8954 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 1061/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0559e-04 - acc: 0.8906Epoch 01060: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0629e-04 - acc: 0.8931 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1062/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8762e-04 - acc: 0.8958Epoch 01061: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9147e-04 - acc: 0.8925 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1063/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9907e-04 - acc: 0.8919Epoch 01062: val_loss improved from 0.00114 to 0.00113, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 3.0036e-04 - acc: 0.8949 - val_loss: 0.0011 - val_acc: 0.8318
Epoch 1064/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0257e-04 - acc: 0.9010Epoch 01063: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0153e-04 - acc: 0.9001 - val_loss: 0.0013 - val_acc: 0.8248
Epoch 1065/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9490e-04 - acc: 0.8945Epoch 01064: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9734e-04 - acc: 0.8914 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1066/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8793e-04 - acc: 0.8991Epoch 01065: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8717e-04 - acc: 0.9007 - val_loss: 0.0012 - val_acc: 0.8435
Epoch 1067/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9540e-04 - acc: 0.8867Epoch 01066: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9683e-04 - acc: 0.8890 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 1068/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9236e-04 - acc: 0.9023Epoch 01067: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9303e-04 - acc: 0.8989 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1069/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9077e-04 - acc: 0.8991Epoch 01068: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9162e-04 - acc: 0.9013 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1070/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9277e-04 - acc: 0.8952Epoch 01069: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9341e-04 - acc: 0.8914 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1071/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8644e-04 - acc: 0.8932Epoch 01070: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8791e-04 - acc: 0.8937 - val_loss: 0.0012 - val_acc: 0.8435
Epoch 1072/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9113e-04 - acc: 0.9030Epoch 01071: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9172e-04 - acc: 0.9042 - val_loss: 0.0013 - val_acc: 0.8458
Epoch 1073/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8454e-04 - acc: 0.8828Epoch 01072: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8535e-04 - acc: 0.8849 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1074/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0204e-04 - acc: 0.9056Epoch 01073: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0080e-04 - acc: 0.9042 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1075/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9343e-04 - acc: 0.9049Epoch 01074: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9462e-04 - acc: 0.9054 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 1076/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8664e-04 - acc: 0.8984Epoch 01075: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8514e-04 - acc: 0.8914 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1077/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9338e-04 - acc: 0.9023Epoch 01076: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9197e-04 - acc: 0.9007 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1078/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0416e-04 - acc: 0.8984Epoch 01077: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0639e-04 - acc: 0.8978 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1079/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9943e-04 - acc: 0.9017Epoch 01078: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0043e-04 - acc: 0.9065 - val_loss: 0.0014 - val_acc: 0.8435
Epoch 1080/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9590e-04 - acc: 0.8926Epoch 01079: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9484e-04 - acc: 0.8937 - val_loss: 0.0014 - val_acc: 0.8154
Epoch 1081/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9952e-04 - acc: 0.8965Epoch 01080: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9934e-04 - acc: 0.8984 - val_loss: 0.0014 - val_acc: 0.8061
Epoch 1082/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0586e-04 - acc: 0.8809Epoch 01081: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.1111e-04 - acc: 0.8791 - val_loss: 0.0011 - val_acc: 0.8294
Epoch 1083/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9300e-04 - acc: 0.8958Epoch 01082: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9616e-04 - acc: 0.8925 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1084/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9355e-04 - acc: 0.8828Epoch 01083: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9303e-04 - acc: 0.8843 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1085/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9297e-04 - acc: 0.8887Epoch 01084: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9207e-04 - acc: 0.8855 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1086/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8800e-04 - acc: 0.9056Epoch 01085: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8983e-04 - acc: 0.9042 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1087/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0347e-04 - acc: 0.8971Epoch 01086: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0333e-04 - acc: 0.8972 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1088/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9494e-04 - acc: 0.8978Epoch 01087: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9532e-04 - acc: 0.8989 - val_loss: 0.0012 - val_acc: 0.8201
Epoch 1089/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9114e-04 - acc: 0.9095Epoch 01088: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8944e-04 - acc: 0.9036 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1090/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7778e-04 - acc: 0.9023Epoch 01089: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7965e-04 - acc: 0.9013 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1091/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8259e-04 - acc: 0.8887Epoch 01090: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8393e-04 - acc: 0.8873 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1092/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8369e-04 - acc: 0.8841Epoch 01091: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8328e-04 - acc: 0.8826 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1093/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8285e-04 - acc: 0.9036Epoch 01092: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8456e-04 - acc: 0.9013 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1094/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7951e-04 - acc: 0.8919Epoch 01093: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8238e-04 - acc: 0.8925 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1095/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8629e-04 - acc: 0.9004Epoch 01094: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8557e-04 - acc: 0.9030 - val_loss: 0.0013 - val_acc: 0.8224
Epoch 1096/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8498e-04 - acc: 0.8945Epoch 01095: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8457e-04 - acc: 0.8954 - val_loss: 0.0013 - val_acc: 0.8435
Epoch 1097/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8661e-04 - acc: 0.8997Epoch 01096: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8991e-04 - acc: 0.8984 - val_loss: 0.0011 - val_acc: 0.8318
Epoch 1098/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9964e-04 - acc: 0.8984Epoch 01097: val_loss improved from 0.00113 to 0.00112, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 2.9772e-04 - acc: 0.9001 - val_loss: 0.0011 - val_acc: 0.8341
Epoch 1099/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9116e-04 - acc: 0.8926Epoch 01098: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9039e-04 - acc: 0.8925 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1100/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9354e-04 - acc: 0.9102Epoch 01099: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9199e-04 - acc: 0.9065 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1101/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9084e-04 - acc: 0.8789Epoch 01100: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9039e-04 - acc: 0.8797 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1102/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9836e-04 - acc: 0.9017Epoch 01101: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0077e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1103/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8745e-04 - acc: 0.9102Epoch 01102: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8637e-04 - acc: 0.9106 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1104/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8098e-04 - acc: 0.8971Epoch 01103: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8043e-04 - acc: 0.8931 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1105/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8734e-04 - acc: 0.8978Epoch 01104: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8945e-04 - acc: 0.8966 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1106/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9077e-04 - acc: 0.8913Epoch 01105: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9086e-04 - acc: 0.8925 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1107/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8410e-04 - acc: 0.9056Epoch 01106: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8516e-04 - acc: 0.9060 - val_loss: 0.0013 - val_acc: 0.8411
Epoch 1108/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9907e-04 - acc: 0.8965Epoch 01107: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9973e-04 - acc: 0.8937 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 1109/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9408e-04 - acc: 0.8984Epoch 01108: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9281e-04 - acc: 0.9013 - val_loss: 0.0014 - val_acc: 0.8318
Epoch 1110/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8803e-04 - acc: 0.8978Epoch 01109: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8827e-04 - acc: 0.8960 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1111/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8515e-04 - acc: 0.8848Epoch 01110: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8334e-04 - acc: 0.8902 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1112/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7792e-04 - acc: 0.9023Epoch 01111: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7994e-04 - acc: 0.9007 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1113/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7395e-04 - acc: 0.9030Epoch 01112: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7418e-04 - acc: 0.9036 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1114/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7951e-04 - acc: 0.8971Epoch 01113: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8029e-04 - acc: 0.8966 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1115/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7778e-04 - acc: 0.8867Epoch 01114: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7756e-04 - acc: 0.8884 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1116/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9028e-04 - acc: 0.9017Epoch 01115: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8986e-04 - acc: 0.9042 - val_loss: 0.0011 - val_acc: 0.8154
Epoch 1117/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 3.0193e-04 - acc: 0.8978Epoch 01116: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 3.0051e-04 - acc: 0.8972 - val_loss: 0.0011 - val_acc: 0.8294
Epoch 1118/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.9975e-04 - acc: 0.8965Epoch 01117: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.9920e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1119/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7919e-04 - acc: 0.8978Epoch 01118: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7803e-04 - acc: 0.8960 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1120/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7849e-04 - acc: 0.8939Epoch 01119: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8093e-04 - acc: 0.8931 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1121/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8202e-04 - acc: 0.9062Epoch 01120: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8296e-04 - acc: 0.9071 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1122/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8399e-04 - acc: 0.8952Epoch 01121: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8690e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1123/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7957e-04 - acc: 0.9017Epoch 01122: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7917e-04 - acc: 0.9013 - val_loss: 0.0012 - val_acc: 0.8224
Epoch 1124/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7117e-04 - acc: 0.9095Epoch 01123: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7178e-04 - acc: 0.9077 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1125/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7752e-04 - acc: 0.9062Epoch 01124: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7745e-04 - acc: 0.9077 - val_loss: 0.0012 - val_acc: 0.8224
Epoch 1126/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7757e-04 - acc: 0.9030Epoch 01125: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7697e-04 - acc: 0.9030 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1127/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8054e-04 - acc: 0.9010Epoch 01126: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7977e-04 - acc: 0.9042 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1128/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7011e-04 - acc: 0.8991Epoch 01127: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7027e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1129/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7449e-04 - acc: 0.8991Epoch 01128: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7661e-04 - acc: 0.8995 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1130/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7957e-04 - acc: 0.9089Epoch 01129: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7905e-04 - acc: 0.9083 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1131/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7311e-04 - acc: 0.8965Epoch 01130: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7370e-04 - acc: 0.8984 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1132/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7852e-04 - acc: 0.9036Epoch 01131: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7715e-04 - acc: 0.9025 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 1133/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7815e-04 - acc: 0.8932Epoch 01132: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7665e-04 - acc: 0.8919 - val_loss: 0.0013 - val_acc: 0.8388
Epoch 1134/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7485e-04 - acc: 0.8939Epoch 01133: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7493e-04 - acc: 0.8972 - val_loss: 0.0012 - val_acc: 0.8435
Epoch 1135/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7006e-04 - acc: 0.8997Epoch 01134: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6988e-04 - acc: 0.8995 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1136/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7281e-04 - acc: 0.9134Epoch 01135: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7380e-04 - acc: 0.9095 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1137/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7267e-04 - acc: 0.9043Epoch 01136: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7453e-04 - acc: 0.9025 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1138/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7315e-04 - acc: 0.8945Epoch 01137: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7480e-04 - acc: 0.8960 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1139/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8118e-04 - acc: 0.9036Epoch 01138: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8085e-04 - acc: 0.8989 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1140/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7266e-04 - acc: 0.8991Epoch 01139: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7383e-04 - acc: 0.9007 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1141/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7829e-04 - acc: 0.9017Epoch 01140: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7810e-04 - acc: 0.9013 - val_loss: 0.0011 - val_acc: 0.8318
Epoch 1142/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7716e-04 - acc: 0.8887Epoch 01141: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7570e-04 - acc: 0.8890 - val_loss: 0.0011 - val_acc: 0.8318
Epoch 1143/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7892e-04 - acc: 0.8952Epoch 01142: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7955e-04 - acc: 0.8954 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1144/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6620e-04 - acc: 0.8939Epoch 01143: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6739e-04 - acc: 0.8925 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 1145/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8545e-04 - acc: 0.9004Epoch 01144: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8550e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8224
Epoch 1146/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7371e-04 - acc: 0.8952Epoch 01145: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7374e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1147/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7310e-04 - acc: 0.9108Epoch 01146: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7352e-04 - acc: 0.9071 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1148/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7212e-04 - acc: 0.9043Epoch 01147: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7140e-04 - acc: 0.9054 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1149/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7070e-04 - acc: 0.9017Epoch 01148: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7051e-04 - acc: 0.9025 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1150/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7611e-04 - acc: 0.9017Epoch 01149: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7693e-04 - acc: 0.9001 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1151/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7623e-04 - acc: 0.8932Epoch 01150: val_loss improved from 0.00112 to 0.00111, saving model to model.h5
1712/1712 [==============================] - 2s - loss: 2.7457e-04 - acc: 0.8966 - val_loss: 0.0011 - val_acc: 0.8341
Epoch 1152/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8520e-04 - acc: 0.9023Epoch 01151: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8382e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1153/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7636e-04 - acc: 0.9017Epoch 01152: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7443e-04 - acc: 0.8978 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1154/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7246e-04 - acc: 0.8991Epoch 01153: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7078e-04 - acc: 0.8995 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1155/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7034e-04 - acc: 0.8887Epoch 01154: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7028e-04 - acc: 0.8902 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1156/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7431e-04 - acc: 0.8997Epoch 01155: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7380e-04 - acc: 0.8960 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1157/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6889e-04 - acc: 0.9030Epoch 01156: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6932e-04 - acc: 0.9007 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1158/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6875e-04 - acc: 0.8965Epoch 01157: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6935e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1159/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6971e-04 - acc: 0.8952Epoch 01158: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6958e-04 - acc: 0.8931 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1160/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6707e-04 - acc: 0.8997Epoch 01159: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6890e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1161/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8014e-04 - acc: 0.8900Epoch 01160: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7768e-04 - acc: 0.8902 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1162/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7423e-04 - acc: 0.8939Epoch 01161: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7624e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1163/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7432e-04 - acc: 0.8978Epoch 01162: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7329e-04 - acc: 0.8966 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1164/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7353e-04 - acc: 0.8997Epoch 01163: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7360e-04 - acc: 0.9001 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1165/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8226e-04 - acc: 0.8971Epoch 01164: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8631e-04 - acc: 0.9007 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1166/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7722e-04 - acc: 0.9004Epoch 01165: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7589e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1167/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6413e-04 - acc: 0.9017Epoch 01166: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6487e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1168/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6656e-04 - acc: 0.8945Epoch 01167: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6669e-04 - acc: 0.8972 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1169/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6413e-04 - acc: 0.9043Epoch 01168: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6370e-04 - acc: 0.8954 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1170/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6840e-04 - acc: 0.9023Epoch 01169: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6933e-04 - acc: 0.9019 - val_loss: 0.0012 - val_acc: 0.8435
Epoch 1171/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7166e-04 - acc: 0.9082Epoch 01170: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7129e-04 - acc: 0.9065 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1172/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6732e-04 - acc: 0.8997Epoch 01171: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6726e-04 - acc: 0.8984 - val_loss: 0.0013 - val_acc: 0.8318
Epoch 1173/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6515e-04 - acc: 0.8906Epoch 01172: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6678e-04 - acc: 0.8931 - val_loss: 0.0014 - val_acc: 0.8294
Epoch 1174/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6841e-04 - acc: 0.8893Epoch 01173: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6909e-04 - acc: 0.8838 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1175/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7552e-04 - acc: 0.8978Epoch 01174: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7546e-04 - acc: 0.8960 - val_loss: 0.0013 - val_acc: 0.8364
Epoch 1176/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7009e-04 - acc: 0.8971Epoch 01175: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7175e-04 - acc: 0.8954 - val_loss: 0.0014 - val_acc: 0.8388
Epoch 1177/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7836e-04 - acc: 0.9010Epoch 01176: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7752e-04 - acc: 0.9042 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1178/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7066e-04 - acc: 0.9030Epoch 01177: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7243e-04 - acc: 0.9001 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 1179/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7233e-04 - acc: 0.8906Epoch 01178: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7092e-04 - acc: 0.8931 - val_loss: 0.0014 - val_acc: 0.8341
Epoch 1180/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7860e-04 - acc: 0.8997Epoch 01179: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7919e-04 - acc: 0.8972 - val_loss: 0.0013 - val_acc: 0.8201
Epoch 1181/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7811e-04 - acc: 0.8952Epoch 01180: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7639e-04 - acc: 0.8919 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 1182/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7438e-04 - acc: 0.8880Epoch 01181: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7421e-04 - acc: 0.8902 - val_loss: 0.0014 - val_acc: 0.8248
Epoch 1183/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.8357e-04 - acc: 0.9004Epoch 01182: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.8183e-04 - acc: 0.8989 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1184/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7685e-04 - acc: 0.9017Epoch 01183: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7816e-04 - acc: 0.8949 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1185/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.7504e-04 - acc: 0.9023Epoch 01184: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.7352e-04 - acc: 0.9013 - val_loss: 0.0012 - val_acc: 0.8318
Epoch 1186/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.5655e-04 - acc: 0.8919Epoch 01185: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.5726e-04 - acc: 0.8937 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1187/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6887e-04 - acc: 0.9043Epoch 01186: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6897e-04 - acc: 0.9042 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1188/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6467e-04 - acc: 0.9036Epoch 01187: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6359e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1189/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6239e-04 - acc: 0.9095Epoch 01188: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6255e-04 - acc: 0.9112 - val_loss: 0.0012 - val_acc: 0.8364
Epoch 1190/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6213e-04 - acc: 0.9043Epoch 01189: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6030e-04 - acc: 0.9042 - val_loss: 0.0012 - val_acc: 0.8248
Epoch 1191/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.5824e-04 - acc: 0.9036Epoch 01190: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.5810e-04 - acc: 0.9060 - val_loss: 0.0012 - val_acc: 0.8271
Epoch 1192/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6390e-04 - acc: 0.8971Epoch 01191: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6400e-04 - acc: 0.8989 - val_loss: 0.0013 - val_acc: 0.8341
Epoch 1193/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6359e-04 - acc: 0.9076Epoch 01192: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6185e-04 - acc: 0.9054 - val_loss: 0.0013 - val_acc: 0.8294
Epoch 1194/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6193e-04 - acc: 0.8971Epoch 01193: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6199e-04 - acc: 0.8960 - val_loss: 0.0012 - val_acc: 0.8388
Epoch 1195/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.5842e-04 - acc: 0.9043Epoch 01194: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.5816e-04 - acc: 0.9025 - val_loss: 0.0011 - val_acc: 0.8318
Epoch 1196/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6321e-04 - acc: 0.9030Epoch 01195: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6308e-04 - acc: 0.9001 - val_loss: 0.0012 - val_acc: 0.8294
Epoch 1197/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6218e-04 - acc: 0.9056Epoch 01196: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6607e-04 - acc: 0.9025 - val_loss: 0.0012 - val_acc: 0.8341
Epoch 1198/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6624e-04 - acc: 0.9004Epoch 01197: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6656e-04 - acc: 0.8966 - val_loss: 0.0012 - val_acc: 0.8411
Epoch 1199/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6801e-04 - acc: 0.8906Epoch 01198: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6950e-04 - acc: 0.8943 - val_loss: 0.0013 - val_acc: 0.8271
Epoch 1200/1200
1536/1712 [=========================>....] - ETA: 0s - loss: 2.6623e-04 - acc: 0.8971Epoch 01199: val_loss did not improve
1712/1712 [==============================] - 2s - loss: 2.6596e-04 - acc: 0.8984 - val_loss: 0.0012 - val_acc: 0.8341

---

Step 7: Visualize the Loss and Test Predictions

(IMPLEMENTATION) Answer a few questions and visualize the loss

Question 1: Outline the steps you took to get to your final neural network architecture and your reasoning at each step.

Answer:

Many different architectures have been proven, resulting in ~200K to ~1.700K trainable parameters. However, the more complex architectures have not had an important achievement, that makes worth the use of such a computationally expensive model, hence the final model is simple. Despite the simplicity of the chosen model, it is been observed that in complex architectures, the dense layers have more impact in the loss decrease whether it is added more dense layers or more parameters to them although that makes the model more prone to overfitting.

Eventually, the chosen model is a stack of four convolution layers. Since every image is 96x96 in greyscale, the resulting input shape for the input tensor will be 96x96x1. It has been observed that more complex architectures -with more convolution layers or more dense layers-, after optimizing properly, the learning of the model was not very smooth and the behaviour of the loss function was rough. For this reason, the final model is simpler although it takes more cycles to train. In order to reduce that time, BatchNorm layers have been used before the activation function needed after each convolution, and the weights have been initialized to 0-centered normal distribution with a standard deviation of 0.02 as it has been suggested in Masked Loss Convolutional Neural Network For Facial Keypoint Detection. However in this architecture, BatchNorm was not helping the model to learn either faster or in a smooth way.

In order to prevent overfitting, dropout layers have been used and GlobalAveragePooling2D instead of Flatten layers, since the first has more impact dimensionality reduction since it is a structural regularizer that explicitly enforces feature maps to be confidence maps of categories. Regarding the strides and filters, different values have been tried. Basically, most of the literature found, use similar values. In this case, this combination has worked with the proposed architecture, using no zero padding, since it was not necessary to keep the information at the borders. Padding can be used as a performance enhancer since the size of the volumes would reduce by a small amount after each CONV, and the information at the borders would be “washed away” too quickly, ensuring that network is only getting useful knowledge for the task.

Finally, for the dense layer, no activation function is applied, which means that the identity or linear transformation is applied. Originally this model had one convolution less and an additional Dense layer, however, the drop layer between the dense layers was preventing the model to achieve a better score. Furthermore, it has been found that applying sigmoid or relu, has no positive impact on the network performance. The resulting output layer attends to the number of parameters needed to identify for this task, 15 abscissa and 15 ordinate coordinates to identify each landmark.

Question 2: Defend your choice of optimizer. Which optimizers did you test, and how did you determine which worked best?

Answer:

Given the proposed model, the optimizer chosen it has been crucial in order to have a good learning curve. The results are shown on the table below. Despite of some optimizers help to achieve better accuracy than others, only the accuracy or the final validation loss, is not enough in order to evaluate if the model is good enough for the task. Depending on the optimizer chosen, the learning curve is very rough and thus, the model is not very good generalizing and fails on the testing set.

Optimizer	Learning rate	Epochs	Observations	Min loss	Min val loss	Accuracy	Testing samples
SGD	0.0015	+1500	Very slow	0.0074	0.0077	~65%	Fair
RMSprop	0.0010	Early stop ~800	Rough	0.0014	0.0021	~77%	Fair
Adam	0.0001	1200	Acc dropping	0.0033	0.0036	-69%	Bad
Adamax	0.0015	Early stop ~940	Smooth	0.0015	0.0022	~75%	Good
Nadam	0.0001	Early stop ~1000	Good, smooth	0.0030	0.0033	~71%	Good

Those optimizers with fair results, detected eyes and nose pretty accurate, but failed to detect the mouth landmarks.

Finally, Adamax was chosen, and no initial learning rate was defined. It achieved ~83% accuracy. Given the sparsity of the data, it makes sense that an adaptive estimator has a better performance than Stochastic gradient descent, which maintains a single learning rate for all weight updates and the learning rate does not change during training, thus it takes longer to converge. Given the nature of the data, with this architecture, Adamax has been proven a better optimizer than Nesterov-Adam. [References: 1|2|3]

Use the code cell below to plot the training and validation loss of your neural network. You may find this resource useful.

## TODO: Visualize the training and validation loss of your neural network

# data in history --> hist.history.keys()

# history for loss
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper right')
plt.xlim(xmin=0) 
plt.xlim(xmax=100)  # adjust the max leaving min unchanged
plt.show()

# history for accuracy
plt.plot(hist.history['acc'])
plt.plot(hist.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='lower right')
#plt.xlim(xmin=0) 
#plt.xlim(xmax=100) 
plt.show()

Question 3: Do you notice any evidence of overfitting or underfitting in the above plot? If so, what steps have you taken to improve your model? Note that slight overfitting or underfitting will not hurt your chances of a successful submission, as long as you have attempted some solutions towards improving your model (such as regularization, dropout, increased/decreased number of layers, etc).

Answer:

Certainly, some architectures are more prone to overfitting than others, especially those with a high complexity level. In order to improve the chances of the model of generalizing well, it has been added dropout layers with different values, besides Early Stopping callback is helpful to save unnecessary computation time. From the plot above, we can see that Early Stopping should have stopped around ~700 epoch in order to prevent overfitting to come up, however, a high patience parameter has been set since lower waiting periods prevented the model to reach a higher accuracy.

Nevertheless, we are not dealing with a vast dataset, therefore overfitting is a known risk for this task, and this is why Data Augmentation would be the best choice here.

Visualize a Subset of the Test Predictions

Execute the code cell below to visualize your model's predicted keypoints on a subset of the testing images.

y_test = model.predict(X_test)
fig = plt.figure(figsize=(20,20))
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)
for i in range(9):
    ax = fig.add_subplot(3, 3, i + 1, xticks=[], yticks=[])
    plot_data(X_test[i], y_test[i], ax)

---

Step 8: Complete the pipeline

With the work you did in Sections 1 and 2 of this notebook, along with your freshly trained facial keypoint detector, you can now complete the full pipeline. That is given a color image containing a person or persons you can now

• Detect the faces in this image automatically using OpenCV
• Predict the facial keypoints in each face detected in the image
• Paint predicted keypoints on each face detected

In this Subsection you will do just this!

(IMPLEMENTATION) Facial Keypoints Detector

Use the OpenCV face detection functionality you built in previous Sections to expand the functionality of your keypoints detector to color images with arbitrary size. Your function should perform the following steps

1. Accept a color image.
2. Convert the image to grayscale.
3. Detect and crop the face contained in the image.
4. Locate the facial keypoints in the cropped image.
5. Overlay the facial keypoints in the original (color, uncropped) image.

Note: step 4 can be the trickiest because remember your convolutional network is only trained to detect facial keypoints in $96 \times 96$ grayscale images where each pixel was normalized to lie in the interval $[0,1]$, and remember that each facial keypoint was normalized during training to the interval $[-1,1]$. This means - practically speaking - to paint detected keypoints onto a test face you need to perform this same pre-processing to your candidate face - that is after detecting it you should resize it to $96 \times 96$ and normalize its values before feeding it into your facial keypoint detector. To be shown correctly on the original image the output keypoints from your detector then need to be shifted and re-normalized from the interval $[-1,1]$ to the width and height of your detected face.

When complete you should be able to produce example images like the one below

# Load in color image for face detection
image = cv2.imread('images/trump_funny_face.jpg')

# Convert the image to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_copy = np.copy(image)

# plot our image
fig = plt.figure(figsize = (9,9))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])
ax1.set_title('image copy')
ax1.imshow(image_copy)

<matplotlib.image.AxesImage at 0x7fd8a52c8d30>

from keras.models import load_model
model = load_model('model.h5')

# Detect facial keypoints or landmarks 
def detect_keypoints(image):
    
    # Convert image to gray scale
    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) 
    
    # Detect number of faces present
    faces = detect_faces(image, 1.4, 3) # faces coordinates
    # print(faces)
    
    image_with_kp = np.copy(image) # image to mark the landmarks  
        
    # for every face found on the image...       
    for (x,y,w,h) in faces: 
        
        # Crop and resize
        face = gray[y:y+h, x:x+w]
        resize = cv2.resize(face, (96, 96))

        # Normalize and reshape to input shape to feed the model
        norm_face = resize / 255 
        norm_face = norm_face.reshape(-1, 96, 96, 1) # return each images as 96 x 96 x 1

        # Apply model to extract the facial keypoints
        kp = model.predict(norm_face) # We apply the model to the already normalized picture face
        kp = kp * 48 + 48 #  utils.py: y = (y - 48) / 48, scale target coordinates to [-1, 1]
        
        # print(kp) # 30 points [x,y,x,y,x,y.....] ----> len(kp)=1 --> kp[0][x], kp[0][y], etc.
                
        # Assign x and y
        _x = kp[0][0::2]  # print("x: ", _x)  --> starts in 0-element and skip 1 until the end [x,y,x,y,x,y.....]
        _y = kp[0][1::2]  # print("y: ", _y)  --> starts in 1-element and skip 1 until the end [x,y,x,y,x,y.....]
        
        # Rescale to print the points on the original image
        _x = x + _x * w / 96
        _y = y + _y * h / 96
        
        cv2.rectangle(image_with_kp, (x,y), (x+w,y+h), (255,0,0), 3)
        
        # For every (x,y) pair...
        for x_kp, y_kp in zip(_x, _y):
            cv2.circle(image_with_kp, (x_kp, y_kp), 1, (0, 255, 0), 3) # ...draw a circle marking the point
             
    return image_with_kp

# Extract the facial landmarks using the model built
image_with_landmarks = detect_keypoints(image)

# Display the image with the keypoints
fig = plt.figure(figsize = (9,9))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])

ax1.set_title('Image with predicted keypoints')
ax1.imshow(image_with_landmarks)

Number of faces detected: 1

<matplotlib.image.AxesImage at 0x7fd8a4bc1358>

(Optional) Further Directions - add a filter using facial keypoints to your laptop camera

Now you can add facial keypoint detection to your laptop camera - as illustrated in the gif below.

The next Python cell contains the basic laptop video camera function used in the previous optional video exercises. Combine it with the functionality you developed for keypoint detection and marking in the previous exercise and you should be good to go!

import cv2
import time 
from keras.models import load_model
def laptop_camera_go():
    # Create instance of video capturer
    cv2.namedWindow("face detection activated")
    vc = cv2.VideoCapture(0)

    # Try to get the first frame
    if vc.isOpened(): 
        rval, frame = vc.read()
    else:
        rval = False
    
    # keep video stream open
    while rval:
        # plot image from camera with detections marked
        cv2.imshow("face detection activated", frame)
        
        # exit functionality - press any key to exit laptop video
        key = cv2.waitKey(20)
        if key > 0: # exit by pressing any key
            # destroy windows
            cv2.destroyAllWindows()
            
            # hack from stack overflow for making sure window closes on osx --> https://stackoverflow.com/questions/6116564/destroywindow-does-not-close-window-on-mac-using-python-and-opencv
            for i in range (1,5):
                cv2.waitKey(1)
            return
        
        # read next frame
        time.sleep(0.05)             # control framerate for computation - default 20 frames per sec
        rval, frame = vc.read()  

# Run your keypoint face painter
laptop_camera_go()

(Optional) Further Directions - add a filter using facial keypoints

Using your freshly minted facial keypoint detector pipeline you can now do things like add fun filters to a person's face automatically. In this optional exercise you can play around with adding sunglasses automatically to each individual's face in an image as shown in a demonstration image below.

To produce this effect an image of a pair of sunglasses shown in the Python cell below.

# Load in sunglasses image - note the usage of the special option
# cv2.IMREAD_UNCHANGED, this option is used because the sunglasses 
# image has a 4th channel that allows us to control how transparent each pixel in the image is
sunglasses = cv2.imread("images/sunglasses_4.png", cv2.IMREAD_UNCHANGED)

# Plot the image
fig = plt.figure(figsize = (6,6))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])
ax1.imshow(sunglasses)
ax1.axis('off');

This image is placed over each individual's face using the detected eye points to determine the location of the sunglasses, and eyebrow points to determine the size that the sunglasses should be for each person (one could also use the nose point to determine this).

Notice that this image actually has 4 channels, not just 3.

# Print out the shape of the sunglasses image
print ('The sunglasses image has shape: ' + str(np.shape(sunglasses)))

It has the usual red, blue, and green channels any color image has, with the 4th channel representing the transparency level of each pixel in the image. Here's how the transparency channel works: the lower the value, the more transparent the pixel will become. The lower bound (completely transparent) is zero here, so any pixels set to 0 will not be seen.

This is how we can place this image of sunglasses on someone's face and still see the area around of their face where the sunglasses lie - because these pixels in the sunglasses image have been made completely transparent.

Lets check out the alpha channel of our sunglasses image in the next Python cell. Note because many of the pixels near the boundary are transparent we'll need to explicitly print out non-zero values if we want to see them.

# Print out the sunglasses transparency (alpha) channel
alpha_channel = sunglasses[:,:,3]
print ('the alpha channel here looks like')
print (alpha_channel)

# Just to double check that there are indeed non-zero values
# Let's find and print out every value greater than zero
values = np.where(alpha_channel != 0)
print ('\n the non-zero values of the alpha channel look like')
print (values)

This means that when we place this sunglasses image on top of another image, we can use the transparency channel as a filter to tell us which pixels to overlay on a new image (only the non-transparent ones with values greater than zero).

One last thing: it's helpful to understand which keypoint belongs to the eyes, mouth, etc. So, in the image below, we also display the index of each facial keypoint directly on the image so that you can tell which keypoints are for the eyes, eyebrows, etc.

With this information, you're well on your way to completing this filtering task! See if you can place the sunglasses automatically on the individuals in the image loaded in / shown in the next Python cell.

# Load in color image for face detection
image = cv2.imread('images/obamas4.jpg')

# Convert the image to RGB colorspace
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)


# Plot the image
fig = plt.figure(figsize = (8,8))
ax1 = fig.add_subplot(111)
ax1.set_xticks([])
ax1.set_yticks([])
ax1.set_title('Original Image')
ax1.imshow(image)

## (Optional) TODO: Use the face detection code we saw in Section 1 with your trained conv-net to put
## sunglasses on the individuals in our test image

(Optional) Further Directions - add a filter using facial keypoints to your laptop camera

Now you can add the sunglasses filter to your laptop camera - as illustrated in the gif below.

The next Python cell contains the basic laptop video camera function used in the previous optional video exercises. Combine it with the functionality you developed for adding sunglasses to someone's face in the previous optional exercise and you should be good to go!

import cv2
import time 
from keras.models import load_model
import numpy as np

def laptop_camera_go():
    # Create instance of video capturer
    cv2.namedWindow("face detection activated")
    vc = cv2.VideoCapture(0)

    # try to get the first frame
    if vc.isOpened(): 
        rval, frame = vc.read()
    else:
        rval = False
    
    # Keep video stream open
    while rval:
        # Plot image from camera with detections marked
        cv2.imshow("face detection activated", frame)
        
        # Exit functionality - press any key to exit laptop video
        key = cv2.waitKey(20)
        if key > 0: # exit by pressing any key
            # Destroy windows 
            cv2.destroyAllWindows()
            
            for i in range (1,5):
                cv2.waitKey(1)
            return
        
        # Read next frame
        time.sleep(0.05)             # control framerate for computation - default 20 frames per sec
        rval, frame = vc.read()    
        

# Load facial landmark detector model
model = load_model('my_model.h5')

# Run sunglasses painter
laptop_camera_go()